Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Tuesday 25 August

Computer Vision

SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs

Ali Bahri, Hang Li, Hongliang Li et al. (+1 more)

Depth pruning removes entire Transformer blocks to reduce the inference cost of large language models, but disrupts the hidden-state distributions expected by downstream layers, leading to significant accuracy loss. We introduce SHIFT-LLM, a training-free post-pruning correction framework that inserts a Linear Residual Adapter (LRA) at each pruning site. Each LRA preserves the identity pathway of the original residual block and adds a lightweight affine residual correction. This correction is calibrated via closed-form least-squares regression on a small held-out set, without gradient computation, to approximate the missing residual update produced by the pruned block. Together with the preserved identity pathway, the resulting LRA output approximates the hidden state produced by the original block, thereby mitigating the distributional mismatch introduced by layer removal while avoiding the expensive attention and feed-forward computations of the removed blocks. The resulting LRAs support low-rank factorization and exact merging across consecutive pruned layers for additional compression, and combine naturally with parameter-efficient fine-tuning for further recovery beyond fine-tuning the pruned model alone. Experiments on five model families, six layer-selection criteria, and seven zero-shot benchmarks show that SHIFT-LLM consistently recovers accuracy lost to depth pruning across most configurations, achieving gains up to +15.7 points on Llama-3.1-8B-Instruct while requiring only a few hundred calibration samples and no gradient computation.
Read the full abstract

All authors Ali Bahri, Hang Li, Hongliang Li, Zhitang Chen

Computer Vision · Cross-listed from cs.AI

CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search

Xiaolong Sun, Qichao Wang, Hangyu Li et al. (+1 more)

Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transient prediction with persistent index admission, and lack explicit risk control over factually incorrect or visually unsupported values. We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Indexing (CVE-SAI), which first infers and freezes an ontology-constrained candidate from the primary image and attribute question without catalog text, and then decides whether that candidate should enter the index. Focus-Zone Distortion (FZD) constructs an attribute-specific visual-dependence proxy through a controlled counterfactual intervention, and Evidence-Guided Attention Redistribution (EGAR) uses the proxy to refine ontology-constrained scoring. The canonical candidate is frozen before evidence necessity, evidence retention, nuisance-transformation stability, and candidate-specific catalog-text conflict audits; catalog text can only tighten admission and cannot revise the candidate. Independent family-level calibration selects one policy with a simultaneous one-sided finite-sample bound under a 5% unsafe-admission budget. Experiments on five visual attributes derived from Amazon Berkeley Objects show that CVE-SAI improves attribute inference and evidence localization, achieves the highest certified admission coverage under the shared risk protocol, and yields the strongest controlled retrieval performance with the lowest unsafe auto-induced exposure among automatic-admission systems. Separating inference from admission therefore enables visually supported attribute completion to improve retrieval while limiting persistent index contamination.
Read the full abstract

All authors Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen

Computer Vision · Cross-listed from cs.CL

Unsupervised Post-Training of Foundation Models: A Survey

Yijie Xu, Qianyi Cai, Huizai Yao et al. (+9 more)

Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80 strict UPT methods and organize them by the object that supplies the update signal: a prediction statistic, a sample relation, a self-generated target, or an internal evaluator. Beyond inventory, we show how the choice of internal signal and task structure determines whether post-training improves the model or recursively amplifies error. An orthogonal Input Visibility $\times$ Update Persistence view maps deployment regimes and defines a unified framework for UPT selection and evaluation.
Read the full abstract

All authors Yijie Xu, Qianyi Cai, Huizai Yao, Yili Wang, Tianfu Wang, Cehao Yang, Xingbo Yao, Zhiyu Guo, Aiwei Liu, Xuming Hu, Weiyu Guo, Hui Xiong

Computer Vision

Targeting the Attention Heads Behind Object Hallucination in LLaVA

Armaan Sandhu, Abhilasha Senapati and Hima Kammachi

Vision-language models such as LLaVA-1.5-7B often hallucinate objects absent from the image when generating captions. We ask whether an interpretability diagnosis of this failure can guide a targeted fix, and we measure what that fix actually changes. We rank attention heads by how much their image attention drops around hallucinated object words, then screen the shortlist by ablating candidate heads and measuring the change in hallucination-token log probability, yielding a 32-head set. We restrict two interventions to these heads: a head-sliced LoRA adapter and an inference-time grounding controller. On 400 held-out COCO images, the combined method lowers CHAIRs (the fraction of captions with a hallucinated object) from 0.370 to 0.230 and CHAIRi (the fraction of hallucinated object mentions) from 0.156 to 0.096 (p < 0.001, paired sign-flip tests). Two controls sharpen attribution. A random-head LoRA control, matched layer-for-layer and trained identically, performs no better than the matched baseline on a separate 200-image control split, supporting the role of head selection rather than LoRA capacity. Under fixed decoding budgets, the CHAIR reduction persists and grows with budget (23% at 64 tokens to 58% at 128), arguing against a pure max-token or truncation artifact, although the method remains shorter and more conservative. The resulting behavior reduces unsupported object mentions while also lowering object recall (0.78 to 0.70). We present a diagnosis-to-intervention pipeline for object hallucination, and, more importantly, a controlled account of what acting on the diagnostic signal actually does: it localizes intervention sites with real, non-random leverage, reported as a behavioral profile rather than a single score.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

Md Selim Sarowar, Md Tanvir Islam, Sungho Kim et al. (+1 more)

Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned queries, and Depth-Aware Chain-of-Thought (DA-CoT) that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters, improving over SpatialVLA by 19.7% relative average success while remaining significantly more parameter-efficient.
Read the full abstract

All authors Md Selim Sarowar, Md Tanvir Islam, Sungho Kim, Sangtae Ahn

Computer Vision

Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping

Yusen Cheng, Lei Fan, Qinfeng Zhu et al. (+3 more)

Data-driven methods are widely used in landslide susceptibility mapping (LSM) because they can effectively model the complex relationships between landslides and geo-environmental conditions. Existing data-driven approaches generally follow two types of data representations. Pixel-based models focus solely on the geo-environmental characteristics of a specific landslide but neglect the influence of its surrounding environment. Patch-based models incorporate surrounding spatial context but may include pixels with weak or no spatial relevance to the target landslide location. To address this limitation, this study proposes a Local-Geo and Spatial Context Fusion (LGSCF) strategy, which synergises the geo-environmental characteristics of landslide points with their corresponding spatial context through a feature-wise modulation mechanism. We tested the LGSCF strategy by integrating it into several representative convolutional neural network (CNN) architectures, creating nine different LGSCF-based models. The primary study area covers approximately 2644 km2 across Jenai and Sinyi Townships in Nantou County, Taiwan, and the dataset comprises 5332 landslide samples and an equal number of non-landslide samples. The results show that LGSCF-based models consistently outperform their corresponding baselines, achieving F1-scores up to 87.09% and AUC values up to 0.9472. Furthermore, the susceptibility maps produced by LGSCF-based models show that known landslides are more accurately concentrated in "very high" susceptibility zones with fewer misclassifications. These findings demonstrate that our fusion strategy can significantly improve the accuracy of landslide susceptibility mapping.
Read the full abstract

All authors Yusen Cheng, Lei Fan, Qinfeng Zhu, Cheng Zhang, Yangyang Li, Ron Mahabir

Computer Vision · Cross-listed from cs.RO

Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning

Sixiang Chen, Jiaming Liu, Jixian Wu et al. (+7 more)

Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithfully reflect arbitrary valid actions. Existing benchmarks are typically confined to expert demonstrations, leaving off-expert action following inadequately evaluated. To address this gap, we introduce WorldEcho, which probes action following over a broader action distribution using visual integrity and SE(3) trajectory alignment. Our diagnosis shows that current world models reasonably execute expert actions but struggle with diverse off-expert trajectories, either ignoring the commanded actions or producing visually invalid rollouts. We further propose WorldSync, which strengthens action following along three complementary axes: distributional coverage, representational grounding, and intervention-effect alignment. It broadens the training distribution over action consequences, grounds intermediate video representations in action-induced robot dynamics through an Action-Forcing Expert, and aligns predicted changes under action interventions with the corresponding changes in ground-truth futures. Experiments on RoboTwin benchmarks and real-robot tasks show that WorldSync improves WorldEcho metrics and serves as a more reliable simulator for iterative policy improvement, enabling policies to achieve higher success rates.
Read the full abstract

All authors Sixiang Chen, Jiaming Liu, Jixian Wu, Yichen Guo, Tinghao Wang, Siyuan Qian, Hao Chen, Jiajun Cao, Jian Tang, Shanghang Zhang

Computer Vision

From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms

Jiangning Zhang, Haojun Chen and Yong Liu

Smart glasses are evolving from capture and display accessories into first-person intelligence platforms that connect human perception, persistent context, and digital or physical action. Their on-body viewpoint aligns with the wearer's vision, audition, motion, and hand-object interaction, but must operate under tight energy, thermal, privacy, and feedback constraints. Despite rapid progress in augmented reality, egocentric vision, multimodal models, human-computer interaction, and embodied intelligence, the literature remains fragmented across devices, tasks, and benchmarks. The key challenge is not whether a model can recognize, answer, remember, or act in isolation, but whether a complete system can sustain a reliable, temporally valid, correctable, and governable perception-state-interaction-action loop. This survey is \textit{the first to systematically study smart glasses through such a unified framework}. We formalize first-person data flow and constrained task utility, characterize devices along eight verifiable hardware capability axes, organize the literature around seven interdependent foundational capabilities, and introduce an L0-L5 framework spanning capture, reactive perception, contextual assistance, persistent state, governed action, and embodied coupling. Across nine application scenes, we connect tasks with datasets, systems, products, stakeholders, failure consequences, and evidence gaps. We further present a nine-dimensional deployment framework, a claim-conditioned evaluation protocol, and an evidence ladder from controlled measurement to longitudinal field validation and audit. Together, these elements make smart glasses more comparable, deployable, and reproducibly evaluated, while outlining a roadmap toward trustworthy first-person intelligence.
Read the full abstract

Computer Vision

LeFlow: Generative Latent Flow Planning for World Models

Hsiang-Wei Huang, Jianxu Shangguan, Junbin Lu et al. (+1 more)

Latent world models are inherently strong encoders that transform image pixel to latent embedding, yet existing world models still rely on online trajectory optimization for action planning: for every state-goal pair, an iterative optimizer is run from scratch to search for optimal action sequences, treating the world model as a black-box simulator. This approach pays the full iterative optimization cost anew at every replanning step and reuses no planning experience across queries. In this work, we ask whether planning itself can be amortized once a latent world model has been learned. We present LeFlow, which learns a reusable latent trajectory prior operating directly in the latent dynamics space from the world model. LeFlow recasts planning as conditional latent trajectory generation: a rectified-flow model imagines a future latent path between the current and goal embeddings, an inverse dynamics decoder turns latent transitions into action chunks, and the frozen world model verifies each candidate by autoregressive rollout. Across four major goal-conditioned pixel-control benchmarks, LeFlow replaces iterative action-space optimization with amortized latent planning and fixed-budget rollout selection, achieving consistent success-rate gains with an order-of-magnitude reduction in planning time. Our results argue that latent world models should support not only prediction but reusable planning priors. Our code is available at https://github.com/hsiangwei0903/LeFlow.
Read the full abstract

All authors Hsiang-Wei Huang, Jianxu Shangguan, Junbin Lu, Jenq-Neng Hwang

Computer Vision

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti et al. (+9 more)

We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl. From these, we download 80M videos with a total duration of 10 million hours. The dataset is designed for multimodal pre-training across the video, audio, and image modalities. Using content-aware scene detection, we extract clips for which we synthetically generate video and audio captions. Models trained on these data achieve competitive performance on standard video-text and audio-text benchmarks, with consistent improvements as training or model scale increases. Additionally, we explore video frames as an alternative source of image-text data by extracting scene-changing frames. These frames exhibit a visual distribution distinct from standard web image corpora, and models trained on this dataset achieve strong image-text retrieval performance. We release LAION-BVD to the research community. It significantly expands open access to multimodal videos at an unprecedented scale.
Read the full abstract

All authors Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti, Andrej Radonjic, Thaddäus Wiedemer, Christoph Schuhmann, Romain Beaumont, Wieland Brendel, Bernhard Schölkopf, A. Sophia Koepke, Jenia Jitsev, Matthias Bethge

Computer Vision

EMFE: A lightweight, explainable machine learning framework for malaria cell classification

Md Abdullah Al Kafi, Walayat Hussain, Mousumi Karmakar et al. (+2 more)

Automated malaria diagnosis from stained blood-smear microscopy is dominated by deep convolutional neural networks that are accurate but computationally expensive, poorly interpretable, and rarely validated with patient-level rigor. We present EMFE (Efficient Mathematical Feature Extraction), a five-feature framework for classifying single red-blood-cell images as parasitized or uninfected using Gray World color normalization, adaptive green-channel thresholding, morphological spot detection, and classical machine learning. Using the NIH LHNCBC malaria dataset (27,558 images from 200 patients), we evaluate Random Forest, Histogram Gradient Boosting, and Support Vector Machine classifiers under patient-grouped nested cross-validation (K_outer=20, K_inner=3), ensuring that cells from each patient remain within a single fold. The optimized Random Forest achieves 94.6% pooled out-of-fold accuracy (95% CI [93.6, 95.7]), corroborated by an untouched 40-patient holdout test (94.3%) and a patient-level permutation test (p<0.001, 1,000 permutations). Ablation experiments quantify the contribution of individual features and pipeline stages. Hardware-matched comparisons with retrained DenseNet121, ResNet50, and MobileNetV2 models assess the accuracy-efficiency trade-off. Synthetic perturbations characterize three failure modes, while explainability analysis identifies spot saturation as the dominant discriminative feature. Patient-level aggregation further quantifies sensitivity-specificity trade-offs and false-positive accumulation. These results demonstrate a statistically rigorous, interpretable, and computationally lightweight alternative to deep learning, while explicitly quantifying its limitations.
Read the full abstract

All authors Md Abdullah Al Kafi, Walayat Hussain, Mousumi Karmakar, Sumit Kumar Banshal, Ahmed Al Marouf

Computer Vision

MoE-based Feature Adapter for Prompt-free Binary Coronary Artery Segmentation in X-ray Angiography

Lin Xi and Yingliang Ma

Accurate segmentation of coronary arteries in X-ray angiography videos is essential for quantitative coronary analysis and image-guided interventions. However, accurate segmentation remains challenging because coronary vessels are thin and exhibit low contrast, while the presence of catheters, guidewires, and complex anatomical background structures can further interfere with vessel delineation. Existing U-Net- and Transformer-based models provide strong baselines, but their shared feature-adaptation pathways may be insufficient for heterogeneous angiographic appearances. In this paper, we propose a prompt-free mixture-of-experts (MoE) feature adapter for binary coronary artery segmentation. Built upon parameter-efficient Vision Transformer adapters, the proposed method uses multiple lightweight experts with input-dependent top-$k$ routing to adaptively refine vessel-related features while limiting active computational cost. Experiments on MOSXAV and external evaluation on XACV show that the proposed method outperforms representative baselines and improves cross-dataset generalisation. These results suggest that MoE-based adapter learning is effective for robust coronary artery segmentation in X-ray angiography videos.
Read the full abstract

Computer Vision

Image Difference Quantification Using Autoencoder-Based Latent Representations

Manish Sharma, Timothy Yim and Clifton Forlines

Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (SSIM) rely on pixel-level comparisons and often fail to capture perceptually meaningful differences between images. In contrast, latent representations learned by deep neural networks encode high-level semantic information that is more closely aligned with human visual perception. This paper proposes a convolutional autoencoder-based framework for quantifying image differences using cosine similarity in latent space. The learned compact embeddings enable robust differentiation between visually distinct images under variations in illumination, pose, and background. Extensive evaluation on dog-cat images and additional cross-domain datasets demonstrates clear class-wise clustering and strong inter-class separability in the latent space, with 98.4% of dog-cat image pairs exhibiting similarity scores below 0.5. Further validation using the TID2013 dataset shows that latent-space distance correlates positively with human Mean Opinion Scores (MOS), demonstrating sensitivity to perceptually relevant image distortions. The proposed approach provides a computationally efficient and semantically grounded alternative to conventional pixel-based similarity metrics, with potential applications in content-based retrieval, perceptual quality assessment, and semantic similarity analysis.
Read the full abstract

Computer Vision

Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy

Md Shahriar Sajid

Brain stroke, known for its high mortality and incidence rates, poses significant health risks and requires rapid intervention for survival. Early diagnosis and preventive measures can greatly reduce life loss and disabilities. Recent advancements in deep learning have led to novel computer-aided diagnostic techniques for early stroke detection. This study proposes an intelligent system that predicts potential strokes using eleven features, evaluated through seven supervised machine learning algorithms. The process includes a literature review, dataset visualization, data preprocessing, and model evaluation. Ensemble methods like Random Forest, Stacking Classifier, and Bagging Classifier achieved high accuracies of 99.52%, while Decision Tree reached 98.24%. Other models, including KNN and TabNet, demonstrated reliable performance, achieving accuracies of 96.73% and 96.49%, respectively. The custom feedforward model achieved 94.91%, while SVC and logistic regression had lower accuracies at 88.06% and 77.03%. The results highlight the effectiveness of ensemble methods in stroke classification.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks

Weimin Zhou

The Bayesian Ideal Observer (IO) establishes the theoretical upper bound on task performance for binary detection tasks. However, analytical computation of the IO test statistic is generally intractable. Numerical approaches based on Markov-chain Monte Carlo (MCMC) methods, including their recent deep generative model-based extensions, typically require extensive posterior sampling for each test image. Supervised learning has also been investigated to approximate the IO performance. However, such methods are typically trained for a specific detection task and signal and may require retraining when the task or signal changes. The score function, defined as the gradient of the log probability density, encodes the local geometry of the data distribution and is a fundamental quantity in modern score-based generative modeling. This work reformulates the IO test statistic in terms of the score function and introduces a score-based ideal observer (SIO). The proposed SIO uses a denoising convolutional neural network trained exclusively on signal-absent images to estimate the signal-absent score function. Once trained, the resulting score model can be used to approximate the IO test statistic for detection tasks involving arbitrary additive signals, without per-image posterior sampling or signal-specific retraining. Numerical studies consider a signal-known-exactly (SKE) detection task with a stochastic lumpy-background model. The results demonstrate that the proposed SIO can closely approximate the IO performance.
Read the full abstract

Computer Vision

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

Muhammad Asad Ali, Umar Khan, Nadia Robertini et al. (+1 more)

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward networks across tasks, which can entangle task behavior and make controlled capability expansion difficult. Sparse Mixture-of-Experts (MoE) decoders provide conditional computation, but token-level learned routing is not naturally aligned with task-level procedural objectives. We propose MoTE (Mixture of Task Experts), a decoder architecture that converts large language model feed-forward networks into task-specific experts while keeping the multimodal backbone shared. Each example follows one sample-level task route, so active task-expert computation remains independent of the number of stored task experts. We instantiate this design as VideoLLM-MoTE and evaluate it on five COIN benchmarks using explicit task routes. The five-expert model activates ~2B LLM parameters per sample and achieves higher average top-1 accuracy than recent VideoLLM baselines. Under the same expert topology, it improves over dense all-expert activation and learned sparse-routing controls. These results show that task-structured routing provides an interpretable and compute-efficient decoder alternative for multi-task video-language learning.
Read the full abstract

All authors Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker

Computer Vision

IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leaves

Feyza Yavuz, Mert Bülent Sar{\i}y{\i}ld{\i}z and Diane Larlus

Multi-teacher distillation has emerged as a way to combine complementary teacher models into a single student model that exhibits the strengths of all its teachers. The student is trained to mimic the output of the teachers on a set of images, typically the union of the individual teacher's training sets, assuming this data is available. In this paper, we question that assumption and explore alternative options. We first study how far one can go when distilling from teachers fed with different types of noise. Then, we show that information contained in the teachers can be leveraged to tailor the noise for multi-teacher distillation: we propose a method that, thanks to decorrelation losses at both patch and image levels, generates teacher-specific, improved samples optimized for data-free distillation. Experiments show that our most effective samples, IDeaL, lead to strong students that successfully capture complementary information from the teachers, yielding surprisingly competitive results that substantially narrow the gap with students distilled from real images. Moreover, given a limited budget of 1K images for distillation, students distilled using our IDeaL samples match or surpass the performance of those distilled using a 1K-image subset of ImageNet.
Read the full abstract

Computer Vision

Weakly Supervised Seafloor Segmentation for Seagrass Habitat Mapping in Side-Scan Sonar Imagery

Hayat Rajani, Nuno Gracias and Rafael Garcia

Seagrass meadows are crucial blue-carbon habitats, and mapping their extent is a prerequisite for coastal management and carbon inventory. Optical satellite sensors cover large areas but cannot reach deep or turbid water, whereas side-scan sonar (SSS) images the seabed at high resolution and at any depth. Interpreting SSS, however, still relies on dense manual annotation, which is slow and costly. We address this by adapting a weakly supervised semantic segmentation framework to SSS benthic habitat mapping, so that pixel-level maps are learned from image-level labels alone. The framework couples a ViT-based encoder-decoder with a classification branch, extracts class activation maps, and refines them into pseudo-labels with a dense conditional random field that we tune for the noise and weak boundaries of acoustic imagery. It follows an iterative self-training scheme, together with a sampling strategy to cope with the strong class imbalance of the data. We also study the effect of different loss functions on segmentation quality, finding Lovász-Softmax loss the most effective. On a held-out transect, the refined pseudo-labels reached an mIoU of 89.3% against the ground truth, and the segmentation branch, trained without any pixel-level labels, reached 87.6%. Self-supervised pretraining on unlabelled SSS added a further 3% in mean intersection-over-union. Field trials further demonstrate the generalizability of the trained model. These results show that accurate and label-efficient benthic habitat mapping from side-scan sonar is feasible at the scale needed for coast-wide seagrass monitoring.
Read the full abstract

Computer Vision

TorchMorph: CUDA-accelerated Morphological Transforms

Kai Zhao

Morphological transforms are long-standing tools for shape and mask processing, but the de facto reference implementation in the Python ecosystem, i.e. scipy.ndimage, is CPU-only, single-array, and therefore unusable inside a GPU training loop without an expensive device-to-host round trip. GPU vision libraries built on PyTorch cover a narrow subset of these operators, typically restricted to two spatial dimensions and flat structuring elements. We present TorchMorph, a lightweight PyTorch extension that closes this gap. TorchMorph exposes 22 public operators covering binary morphology, greyscale morphology, exact and approximate distance transforms, and entropy-regularised optimal transport, all implemented as fused CUDA kernels that operate directly on (B, C, Spatial...) CUDA tensors with up to eight spatial dimensions. The API deliberately mirrors scipy.ndimage argument-for-argument, including border modes, structuring-element origins and pre-allocated outputs, so that existing pipelines port with a change of import. We describe the layered architecture and the kernel designs behind each operator family. Against single-threaded CPU references, batched execution reaches up to 1.1e3 times the throughput of scipy.ndimage on greyscale morphology and up to 350x on exact Euclidean distance transforms, while the Sinkhorn solver runs up to 42x faster than POT. Binary and chamfer operators reproduce their SciPy counterparts exactly, and every float-valued operator agrees with the CPU reference to within 1.8e-6 absolute error. TorchMorph is released under the MIT licence at https://intcomp.github.io/tm.
Read the full abstract

Computer Vision

Interpretable Fundus Image Classification via Ring-Based Retinal Vasculature Features

Xiaoyan Li, Shixin Xu, Arvind Gupta et al. (+1 more)

Retinal fundus photography is widely used for screening and monitoring ocular diseases, but many modern classification pipelines rely on deep latent representations and provide limited interpretability. This study develops an interpretable fundus image classification framework based on a ring-structured representation of the retinal vasculature centered on the optic disc. The method quantifies vessel geometry, color appearance, oxygenation-related vascular appearance, and vessel–background entropy within concentric retinal regions. These physiologically motivated descriptors are derived from vessel masks, image intensities, and optical-density measurements and aggregated across rings to capture spatial variation in vascular properties. Using only quantitative vascular descriptors, the proposed method achieved strong classification performance across three public fundus datasets. On HRF, it achieved 91.1% accuracy using automatically generated vessel masks, matching RETFound, a vision transformer pretrained on large-scale retinal fundus image data, under the same evaluation setting. Additional analyses suggest that pretrained image models are sensitive to acquisition-related spatial cues, including fundus scale and retinal position within the field of view, as well as broader non-vessel image characteristics. This framework may support interpretable disease classification, quantitative retinal phenotyping, and retinal biomarker discovery without requiring large task-specific training datasets.
Read the full abstract

All authors Xiaoyan Li, Shixin Xu, Arvind Gupta, Huaxiong Huang

Computer Vision

Deep Learning Super Resolution for Satellite Cloud Mask Downscaling

Angelos Georgakis, Valentina Kanaki, Giorgos Giannopoulos et al. (+4 more)

A vast amount of optical satellite data is being transmitted to Earth-based servers every day, and more than half of this data is affected by haze or clouds. Additionally, this data suffers from the fundamental trade-off between spatial and temporal resolution, which remains largely unresolved, making the acquisition of continuous high-resolution satellite observations of clouds an ongoing challenge. This work addresses this challenge by proposing two Deep Learning super-resolution methods for the accurate downscaling of SEVIRI cloud mask products, as well as a novel cross-sensor cloud mask dataset called SEVMOD-CM, created by spatially and temporally matching MODIS and SEVIRI satellite observations. The two proposed models are a CNN-based (SpatialCNN) and a GAN-based (SpatialGAN) Neural Network. Trained on the SEVIRI spectral and cloud mask products, the proposed methods predict the corresponding MODIS Cloud masks, achieving a 4x spatial enhancement across sensor domains. Both approaches are evaluated experimentally, and compared against the standard bicubic interpolation upsampling technique. The experimental results demonstrate the value of the proposed models and dataset for the remote sensing community, highlighting the benefits of applying super-resolution techniques to geostationary-derived cloud mask products for applications such as atmospheric monitoring, weather forecasting, disaster risk reduction, solar energy forecasting, and climate research.
Read the full abstract

All authors Angelos Georgakis, Valentina Kanaki, Giorgos Giannopoulos, Stella Girtsou, Ioannis Kontogiorgakis, Charalampos Kontoes, Kostas Philippopoulos

Computer Vision

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

Wenxuan Shen, Dongna Jin and Dongping Chen

Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-the-wild gameplay videos. However, raw gameplay footage entangles the game world with screen-space interfaces, introducing game-specific biases and irrelevant dynamics that hinder world-model training. To address this problem, we introduce GameUI-Taxonomy and G2WEngine, a full-stack framework that formalizes gameplay UI grounding and removal. G2WEngine automatically extracts reusable UI assets from real gameplay videos and synthesizes temporally coherent UI overlays on clean footage. Using this engine, we construct Game2World, comprising 96K synthetic paired videos with precise reconstruction targets and 1,079 in-the-wild clips from 303 games for realistic evaluation. Its asset library contains 5,132 verified UI elements across 21 taxonomy categories, collected from 1,010 representative gameplay frames. Based on Game2World, we propose GameCleaner, a mask-free gameplay UI removal model that combines multimodal semantic understanding with video editing capabilities. Unlike mask-based methods, GameCleaner directly identifies and removes diverse HUD elements while preserving the underlying scene content and temporal dynamics. In a controlled pilot, world models trained on UI-free gameplay improve overall VideoReward by 6.83% over those trained on UI-overlaid data. On UI-removal evaluation, GameCleaner achieves an average AAR of 95.36 on synthetic videos, outperforming the strongest temporal mask baseline by 57.3%, and obtains the best in-the-wild AAR of 80.05 with 99.8 background preservation. These results demonstrate the scalable potential of transforming Internet gameplay videos into high-quality world-model training data. Code, dataset, and model will be available at https://github.com/Dongping-Chen/Game2World.
Read the full abstract

Computer Vision

TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation

Xiaoda Yang, Yuxiang Liu, Kaiwen Zheng et al. (+12 more)

Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal computation of large models make inference prohibitively expensive. We present TurboT2VA, a distillation and inference framework for accelerating a 19B-parameter joint video-audio model. Large-scale T2VA distillation is challenged by modality-imbalanced optimization, the difficulty of continuous-time consistency training at scale, and the quality–diversity trade-off. TurboT2VA addresses these issues with per-modality normalization and a progressive curriculum comprising discrete consistency warm-up, continuous consistency refinement, and joint consistency–distribution matching. The curriculum first establishes a stable, diverse generation trajectory and only then introduces distribution-level refinement. On LTX-2, four-step distillation reduces generator latency from 50.52s to 2.51s at the standard evaluation resolution of 512$\times$768, achieving a 20.1$\times$ speedup while maintaining strong visual quality, audio fidelity, diversity, and video-audio synchronization. We further develop an architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths. Under the high-resolution deployment setting at 1024$\times$1792, the complete stack reduces generator latency from 318.74s to 5.83s on one NVIDIA H20, achieving a 54.67$\times$ generator-only speedup. Inference code and generation demos are available at https://github.com/thu-ml/TurboDiffusion/tree/main/turbot2va.
Read the full abstract

All authors Xiaoda Yang, Yuxiang Liu, Kaiwen Zheng, Yuan Liu, Yibo Lai, Shengpeng Ji, Kai Jiang, Jianfei Chen, Shan Yang, Sen Liang, Xiaobin Hu, Shuicheng Yan, Jintao Zhang, Jun Zhu, Zhou Zhao

Computer Vision

ReGround-Surg: Reliability-Guided Anchor Grounding for Referring Surgical Video Segmentation

Jiaxin Wen, Ming Yin, Lu Liu et al. (+1 more)

Referring surgical video segmentation requires segmenting a target instrument or tissue region across video frames according to a natural language expression. Recent Segment Anything Model 2 (SAM2) based two-stage methods (e.g., ReSurgSAM2) first ground the referred target in an initial or selected frame, then propagate the selected mask via tracking. Although effective, their performance is highly sensitive to the quality of the initial grounded mask: once an incorrect anchor is selected, subsequent tracking tends to propagate the error. This issue is especially challenging in surgical videos due to visually similar instruments, occlusion, and complex tissue-tool interactions. To address this issue, we propose ReGround-Surg, a lightweight reliability-guided anchor grounding framework to improve SAM2-based referring surgical video segmentation. It first predicts a text-conditioned spatial reliability map from the referring expression and current-frame visual features. The map is then reused in two complementary branches: a Gated Side Adapter enhances expression-relevant visual regions before text-to-vision fusion, while a Reliability-Weighted Vision-to-Text Attention module suppresses off-target visual evidence during prompt-token aggregation. Experiments on Ref-EndoVis17 and Ref-EndoVis18 show consistent improvements over state-of-the-art methods across three evaluation splits with negligible speed reduction. Code is publicly available at https://github.com/JiaxinWen1/ReGround-Surg.
Read the full abstract

All authors Jiaxin Wen, Ming Yin, Lu Liu, Zeyu Fu

Computer Vision

On-Policy Self-Distillation in Diffusion Models

Wei Zhou, Xiongwei Zhu, Lingdong Kong et al. (+14 more)

Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.
Read the full abstract

All authors Wei Zhou, Xiongwei Zhu, Lingdong Kong, Bo Chen, Lei Zhang, Yongyuan Liang, Xiaoxia Hou, Ye Tian, Xian Sun, Yingshuo Wang, Linfeng Li, Shengqiong Wu, Leigang Qu, Feng Li, Wei Liu, Julian McAuley, Tat-Seng Chua

Computer Vision

Towards Reliable AI-Based Histological Staining: A Systematic Study of Scaling and Uncertainty in Unpaired Generative Models

Qasim Siddiqui, Adrian Friebel, Maiju Myllys et al. (+4 more)

Liver fibrosis, the principal predictor of long-term outcome in chronic liver disease, is staged from histological estimates of collagen content. Sirius Red (SR) provides the standard quantitative readout (collagen proportionate area, CPA) but is not acquired at every clinical centre and consumes tissue, time, and reagent cost beyond the routine Hematoxylin and eosin (H&E) stain. AI-based virtual staining can generate SR directly from H&E, yet systematic benchmarks of unsupervised models are scarce and their predictive uncertainty has not been quantified, even though visually plausible outputs may not faithfully reproduce the underlying tissue structure. We therefore benchmark six unsupervised image-to-image architectures (GAN-based and diffusion-based) across 54 scaling configurations on a newly released paired H&E to SR mouse liver dataset, the first open resource for this translation task. Each configuration is evaluated jointly on perceptual, distributional, and task-specific axes plus a blinded expert reader study; the best per family is then retrained as a deep ensemble, the first systematic comparison of epistemic uncertainty across unsupervised stain-to-stain architectures. Across families, perceptual quality, task-specific error, and ensemble agreement measure largely independent axes of model fitness: GAN-based methods cluster tightly on perceptual metrics yet differ substantially on task error and ensemble agreement, while the diffusion-based method (CycleDiffusion) is qualitatively different on all three. No single metric captures these differences, so reliable virtual staining requires reporting and selecting on all three jointly. The dataset, tiling pipeline, models, and evaluation code are released publicly.
Read the full abstract

All authors Qasim Siddiqui, Adrian Friebel, Maiju Myllys, Zaynab Hobloss, Daniela Gonzalez, Ahmed Ghallab, Stefan Hoehme

Computer Vision

Comparative Assessment of Deep Learning Architectures for Underwater Subsurface Kelp Forest Segmentation with The Kelp-o-Tron

Sundarabalan Balasubramanian, César Borja, Ana C. Murillo et al. (+5 more)

Submerged kelp forests are vital coastal ecosystems that support marine biodiversity and ecosystem dynamics, yet accurate underwater kelp segmentation remains challenging due to optical degradation, illumination variability, turbidity, overlapping vegetation, and complex benthic backgrounds. We systematically evaluated three deep learning semantic segmentation frameworks, ResNet34-U-Net, ResNet50-DeepLabV3, and a hybrid ResNet50-ASPP-Transformer architecture, for kelp detection using high-resolution underwater RGB imagery collected from northeastern U.S. coastal waters. A dataset of 3,395 SSeg assisted annotated image-mask pairs was developed for model training and validation, while geographically independent sites were used for quantitative and qualitative evaluation. All models used consistent preprocessing, augmentation, and evaluation protocols. On independent test data, ResNet50-DeepLabV3 achieved the highest Dice (0.7120) and Intersection over Union (IoU; 0.6267), followed by ResNet34 U Net (Dice 0.6868; IoU 0.5978). The hybrid ASPP Transformer achieved the highest pixel accuracy (0.8528) but lower Dice (0.6437) and IoU (0.5746). External qualitative evaluation further showed that DeepLabV3 produced more consistent segmentation across varying environmental conditions, image qualities, and benthic habitats. Overall, ResNet50-DeepLabV3, termed Kelp-O-Tron, provided the best balance of segmentation accuracy, robustness, and generalization. The dataset, annotation workflow, and comparative evaluation provide resources for advancing automated underwater habitat mapping and ecological monitoring.
Read the full abstract

All authors Sundarabalan Balasubramanian, César Borja, Ana C. Murillo, Lexi N. Wilkes, Meredith L. McPherson, Kira A. Krumhansl, Jennifer A. Dijkstra, Jarrett E. K. Byrnes

Computer Vision

Human-Inspired Social Engagement Analysis via Interpretable Mutual Visual Attention

Urwa Fatima, Mohammad Zohaib, Francesca Odone et al. (+1 more)

Understanding social interactions from non-verbal visual data is important for behavior analysis and activity monitoring. We propose an interpretable computational model of social engagement inspired by psychological theories of mutual visual attention. Rather than learning interaction patterns end-to-end, our framework explicitly models dyadic visual attention and aggregates these cues into interpretable measures of individual and group engagement. The resulting modular framework combines state-of-the-art head orientation estimation with lightweight geometric reasoning, producing explanations that remain accessible to non-technical users. We evaluate the proposed approach on a variety of data through quantitative experiments and demonstrate its practical usefulness with qualitative visualizations designed to support teachers, caregivers, and social workers in understanding group interaction dynamics.
Read the full abstract

All authors Urwa Fatima, Mohammad Zohaib, Francesca Odone, Nicoletta Noceti

Computer Vision

X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis

Sonali Godavarthy, Matthias Neuwirth-Trapp, Tim-Felix Faasch et al. (+4 more)

Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, sensor types, viewpoints, and domains to enable combinatorial generalization. This should let the model synthesize novel factor combinations unobserved in the training data, such as pairing a fisheye lens with an event sensor never observed in training data. Recent work, MULTI, introduced learnable, factor-specific embeddings to disentangle imaging factors, along with the Factor Alignment Accuracy (FAA) metric to evaluate disentanglement quality. We identify and address two independent limitations. First, MULTI's pixel-level reconstruction objective supervises the model only on observed imaging factor combinations, providing no direct training signal for novel combinations. We therefore propose X-MULTI, which uses a pretrained vision-language model (VLM) to supervise novel factor combinations synthesized during training. Second, we show the FAA metric exhibits severe cross-factor correlation leakage, misrepresenting true disentanglement quality. We therefore propose Improved-FAA (I-FAA), which employs factor-specific augmentation strategies to break these correlations and enables more rigorous evaluation. Experiments demonstrate that X-MULTI achieves improved factor alignment on novel combinations compared to MULTI. Moreover, we show that correlation leakage in FAA distorts the evaluation of true factor disentanglement and I-FAA reduces this leakage and therefore provides a more robust assessment of factor alignment.
Read the full abstract

All authors Sonali Godavarthy, Matthias Neuwirth-Trapp, Tim-Felix Faasch, Maarten Bieshaar, Michael Moeller, Kristof Van Laerhoven, Danda Pani Paudel

Computer Vision

KLTNet: Learning Sparse Feature Tracking for Robust and Accurate Monocular Visual-Inertial Odometry

Renbiao Jin, Danping Zou and Wenxian Yu

Many feature-based visual-inertial odometry (VIO) systems rely on sparse feature tracking, whose accuracy and robustness directly affect state estimation. Classical KLT trackers rely primarily on local image patches and can become unreliable under rapid motion or in low-texture environments. We propose KLTNet, a lightweight learning-based, plug-and-play sparse feature tracker designed to replace classical KLT trackers in KLT-based VIO front ends. KLTNet follows a coarse-to-fine, dense-to-sparse architecture that combines low-resolution dense optical flow for robust global motion initialization with triplet-patch refinement for accurate and temporally consistent tracking. A fixed reference patch provides a stable anchor throughout each feature track and helps reduce accumulated tracking drift. In addition, KLTNet predicts anisotropic confidence weights supervised through differentiable multi-view triangulation, which can be used as observation weights in compatible VIO estimators. Experiments with VINS-Mono and OpenVINS on public benchmarks and a self-collected low-texture dataset demonstrate improved tracking and odometry accuracy over classical KLT, while maintaining real-time performance on an embedded platform.
Read the full abstract