Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Friday 14 November
Bark beetle infestations represent a serious challenge for maintaining the health of coniferous forests. This paper proposes a few-shot learning approach leveraging contrastive learning to detect bark beetle infestations using satellite PRISMA hyperspectral data. The methodology is based on a contrastive learning framework to pre-train a one-dimensional CNN encoder, enabling the extraction of robust feature representations from hyperspectral data. These extracted features are subsequently utilized as input to support vector regression estimators, one for each class, trained on few labeled samples to estimate the proportions of healthy, attacked by bark beetle, and dead trees for each pixel. Experiments on the area of study in the Dolomites show that our method outperforms the use of original PRISMA spectral bands and of Sentinel-2 data. The results indicate that PRISMA hyperspectral data combined with few-shot learning offers significant advantages for forest health monitoring.
Computer Vision
Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays
Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with CT-based Agatston scoring widely regarded as the clinical gold standard. However, CT is costly and impractical for large-scale screening, while chest X-rays (CXRs) are inexpensive but lack reliable ground truth labels, constraining deep learning development. Digitally reconstructed radiographs (DRRs) offer a scalable alternative by projecting CT volumes into CXR-like images while inheriting precise labels. In this work, we provide the first systematic evaluation of DRRs as a surrogate training domain for CAC detection. Using 667 CT scans from the COCA dataset, we generate synthetic DRRs and assess model capacity, super-resolution fidelity enhancement, preprocessing, and training strategies. Lightweight CNNs trained from scratch outperform large pretrained networks; pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean AUC of 0.754, comparable to or exceeding prior CXR-based studies. These results establish DRRs as a scalable, label-rich foundation for CAC detection, while laying the foundation for future transfer learning and domain adaptation to real CXRs.
Read the full abstract
Computer Vision
A Space-Time Transformer for Precipitation Nowcasting
Until recently, numerical weather prediction (NWP) models have stood rivalless in operational forecasting despite a few limitations. Namely, physically-based models are computationally demanding and struggle at short lead times, reducing their utility for nowcasting. Motivated by these shortcomings, recent work proposes AI-weather prediction (AI-WP) alternatives that emulate analysis data with neural networks. While these data-driven approaches have achieved high skill for medium-range forecasting-applications of AI-WP to precipitation and to nowcasting are less explored. To these ends, this paper discusses SaTformer: a video transformer adapted for precipitation nowcasting. To ameliorate some problems related to what is essentially a fat-tailed regression task, we find it prudent to formulate nowcasting as a classification problem and employ a frequency-weighted loss. This straightforward approach scored first on the NeurIPS Weather4Cast 2025 “Cumulative Rainfall” challenge. Code and model weights are available: \texttt{\href{github.com/leharris3/w4c-25}{github.com/leharris3/satformer}}.
Read the full abstract
Computer Vision
SplineSplat: 3D Ray Tracing for Higher-Quality Tomography
We propose a method to efficiently compute tomographic projections of a 3D volume represented by a linear combination of shifted B-splines. To do so, we propose a ray-tracing algorithm that computes 3D line integrals with arbitrary projection geometries. One of the components of our algorithm is a neural network that computes the contribution of the basis functions efficiently. In our experiments, we consider well-posed cases where the data are sufficient for accurate reconstruction without the need for regularization. We achieve higher reconstruction quality than traditional voxel-based methods.
Read the full abstract
Computer Vision
Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids
Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks, such as dispensing, aspiration, and mixing, must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks. The dataset and code are available at https://dualtransparency.github.io/Phys-Liquid/.
Read the full abstract
Computer Vision
Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
While generative models have seen significant adoption across a wide range of data modalities, including 3D data, a consensus on which model is best suited for which task has yet to be reached. Further, conditional information such as text and images to steer the generation process are frequently employed, whereas others, like partial 3D data, have not been thoroughly evaluated. In this work, we compare two of the most promising generative models–Denoising Diffusion Probabilistic Models and Autoregressive Causal Transformers–which we adapt for the tasks of generative shape modeling and completion. We conduct a thorough quantitative evaluation and comparison of both tasks, including a baseline discriminative model and an extensive ablation study. Our results show that (1) the diffusion model with continuous latents outperforms both the discriminative model and the autoregressive approach and delivers state-of-the-art performance on multi-modal shape completion from a single, noisy depth image under realistic conditions and (2) when compared on the same discrete latent space, the autoregressive model can match or exceed diffusion performance on these tasks.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
Boosting Neural Video Representation via Online Structural Reparameterization
Neural Video Representation~(NVR) is a promising paradigm for video compression, showing great potential in improving video storage and transmission efficiency. While recent advances have made efforts in architectural refinements to improve representational capability, these methods typically involve complex designs, which may incur increased computational overhead and lack the flexibility to integrate into other frameworks. Moreover, the inherent limitation in model capacity restricts the expressiveness of NVR networks, resulting in a performance bottleneck. To overcome these limitations, we propose Online-RepNeRV, a NVR framework based on online structural reparameterization. Specifically, we propose a universal reparameterization block named ERB, which incorporates multiple parallel convolutional paths to enhance the model capacity. To mitigate the overhead, an online reparameterization strategy is adopted to dynamically fuse the parameters during training, and the multi-branch structure is equivalently converted into a single-branch structure after training. As a result, the additional computational and parameter complexity is confined to the encoding stage, without affecting the decoding efficiency. Extensive experiments on mainstream video datasets demonstrate that our method achieves an average PSNR gain of 0.37-2.7 dB over baseline methods, while maintaining comparable training time and decoding speed.
Read the full abstract
Computer Vision
S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation
Radiology Report Generation (RRG) aims to automatically generate diagnostic reports from radiology images. To achieve this, existing methods have leveraged the powerful cross-modal generation capabilities of Multimodal Large Language Models (MLLMs), primarily focusing on optimizing cross-modal alignment between radiographs and reports through Supervised Fine-Tuning (SFT). However, by only performing instance-level alignment with the image-text pairs, the standard SFT paradigm fails to establish anatomically-grounded alignment, where the templated nature of reports often leads to sub-optimal generation quality. To address this, we propose S2D-Align, a novel SFT paradigm that establishes anatomically-grounded alignment by leveraging auxiliary signals of varying granularities. S2D-Align implements a shallow-to-deep strategy, progressively enriching the alignment process: it begins with the coarse radiograph-report pairing, then introduces reference reports for instance-level guidance, and ultimately utilizes key phrases to ground the generation in specific anatomical details. To bridge the different alignment stages, we introduce a memory-based adapter that empowers feature sharing, thereby integrating coarse and fine-grained guidance. For evaluation, we conduct experiments on the public MIMIC-CXR and IU X-Ray benchmarks, where S2D-Align achieves state-of-the-art performance compared to existing methods. Ablation studies validate the effectiveness of our multi-stage, auxiliary-guided approach, highlighting a promising direction for enhancing grounding capabilities in complex, multi-modal generation tasks.
Read the full abstract
Computer Vision
From Retinal Pixels to Patients: Evolution of Deep Learning Research in Diabetic Retinopathy Screening
Diabetic Retinopathy (DR) remains a leading cause of preventable blindness, with early detection critical for reducing vision loss worldwide. Over the past decade, deep learning has transformed DR screening, progressing from early convolutional neural networks trained on private datasets to advanced pipelines addressing class imbalance, label scarcity, domain shift, and interpretability. This survey provides the first systematic synthesis of DR research spanning 2016-2025, consolidating results from 50+ studies and over 20 datasets. We critically examine methodological advances, including self- and semi-supervised learning, domain generalization, federated training, and hybrid neuro-symbolic models, alongside evaluation protocols, reporting standards, and reproducibility challenges. Benchmark tables contextualize performance across datasets, while discussion highlights open gaps in multi-center validation and clinical trust. By linking technical progress with translational barriers, this work outlines a practical agenda for reproducible, privacy-preserving, and clinically deployable DR AI. Beyond DR, many of the surveyed innovations extend broadly to medical imaging at scale.
Read the full abstract
Computer Vision
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically estimating sparse attention patterns at each denoising step incurs high computational overhead and estimation errors, while static sparsity patterns remain fixed and often suboptimal throughout denoising. We identify a key structural property of diffusion attention, namely, its sparsity patterns exhibit strong temporal coherence across denoising steps. Tiles deemed non-essential at step $t$ typically remain so at step $t+\delta$. Leveraging this observation, we introduce LiteAttention, a method that exploits temporal coherence to enable evolutionary computation skips across the denoising sequence. By marking non-essential tiles early and propagating skip decisions forward, LiteAttention eliminates redundant attention computations without repeated profiling overheads, combining the adaptivity of dynamic methods with the efficiency of static ones. We implement a highly optimized LiteAttention kernel on top of FlashAttention and demonstrate substantial speedups on production video diffusion models, with no degradation in quality. The code and implementation details will be publicly released.
Read the full abstract
Computer Vision
CareCom: Generative Image Composition with Calibrated Reference Features
Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.
Read the full abstract
Computer Vision
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
Low-Rank Adaptation (LoRA) fusion enables the composition of subject and style representations for controllable generation without retraining. However, existing approaches primarily operate through weight-level merging, without explicitly modeling how independently trained LoRAs interact in the shared parameter space. We adopt a geometric perspective on LoRA fusion, interpreting content and style LoRAs as occupying overlapping, non-orthogonal low-rank subspaces, where such overlap can lead to conflicting parameter updates that affect generation quality. This observation motivates us to reformulate LoRA fusion not merely as parameter combination, but as a problem of controlling how updates from overlapping subspaces are combined. Based on this insight, we propose Null Space Projection LoRA (NP-LoRA), a training-free framework that employs projection as a fusion operator to explicitly modulate cross-LoRA interactions. Specifically, NP-LoRA uses principal directions of the style LoRA to define a projection subspace and projects the content LoRA onto the complementary subspace (i.e., the null space of the style LoRA), suppressing interference along dominant style directions while preserving complementary information. To avoid the overly aggressive suppression of hard projection, we further formulate soft projection as a regularized optimization problem that balances content preservation against style-subspace suppression. This objective admits a closed-form solution, yielding a projection operator controlled by a single parameter that continuously interpolates between linear merging and hard projection. Extensive experiments across multiple pretrained LoRA pairs show that NP-LoRA achieves more balanced content-style composition compared to strong baselines, without requiring retraining. Code is available at https://github.com/blackzebra7/NP-LoRA.
Read the full abstract
Computer Vision
PINGS-X: Physics-Informed Normalized Gaussian Splatting with Axes Alignment for Efficient Super-Resolution of 4D Flow MRI
4D flow magnetic resonance imaging (MRI) is a reliable, non-invasive approach for estimating blood flow velocities, vital for cardiovascular diagnostics. Unlike conventional MRI focused on anatomical structures, 4D flow MRI requires high spatiotemporal resolution for early detection of critical conditions such as stenosis or aneurysms. However, achieving such resolution typically results in prolonged scan times, creating a trade-off between acquisition speed and prediction accuracy. Recent studies have leveraged physics-informed neural networks (PINNs) for super-resolution of MRI data, but their practical applicability is limited as the prohibitively slow training process must be performed for each patient. To overcome this limitation, we propose PINGS-X, a novel framework modeling high-resolution flow velocities using axes-aligned spatiotemporal Gaussian representations. Inspired by the effectiveness of 3D Gaussian splatting (3DGS) in novel view synthesis, PINGS-X extends this concept through several non-trivial novel innovations: (i) normalized Gaussian splatting with a formal convergence guarantee, (ii) axes-aligned Gaussians that simplify training for high-dimensional data while preserving accuracy and the convergence guarantee, and (iii) a Gaussian merging procedure to prevent degenerate solutions and boost computational efficiency. Experimental results on computational fluid dynamics (CFD) and real 4D flow MRI datasets demonstrate that PINGS-X substantially reduces training time while achieving superior super-resolution accuracy. Our code and datasets are available at https://github.com/SpatialAILab/PINGS-X.
Read the full abstract
Computer Vision
Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval
With the daily influx of 3D data on the internet, text-3D retrieval has gained increasing attention. However, current methods face two major challenges: Hierarchy Representation Collapse (HRC) and Redundancy-Induced Saliency Dilution (RISD). HRC compresses abstract-to-specific and whole-to-part hierarchies in Euclidean embeddings, while RISD averages noisy fragments, obscuring critical semantic cues and diminishing the model's ability to distinguish hard negatives. To address these challenges, we introduce the Hyperbolic Hierarchical Alignment Reasoning Network (H$^{2}$ARN) for text-3D retrieval. H$^{2}$ARN embeds both text and 3D data in a Lorentz-model hyperbolic space, where exponential volume growth inherently preserves hierarchical distances. A hierarchical ordering loss constructs a shrinking entailment cone around each text vector, ensuring that the matched 3D instance falls within the cone, while an instance-level contrastive loss jointly enforces separation from non-matching samples. To tackle RISD, we propose a contribution-aware hyperbolic aggregation module that leverages Lorentzian distance to assess the relevance of each local feature and applies contribution-weighted aggregation guided by hyperbolic geometry, enhancing discriminative regions while suppressing redundancy without additional supervision. We also release the expanded T3DR-HIT v2 benchmark, which contains 8,935 text-to-3D pairs, 2.6 times the original size, covering both fine-grained cultural artefacts and complex indoor scenes. Our codes are available at https://github.com/liwrui/H2ARN.
Read the full abstract
Computer Vision
SemanticNN: Compressive and Error-Resilient Semantic Offloading for Extremely Weak Devices
With the rapid growth of the Internet of Things (IoT), integrating artificial intelligence (AI) on extremely weak embedded devices has garnered significant attention, enabling improved real-time performance and enhanced data privacy. However, the resource limitations of such devices and unreliable network conditions necessitate error-resilient device-edge collaboration systems. Traditional approaches focus on bit-level transmission correctness, which can be inefficient under dynamic channel conditions. In contrast, we propose SemanticNN, a semantic codec that tolerates bit-level errors in pursuit of semantic-level correctness, enabling compressive and resilient collaborative inference offloading under strict computational and communication constraints. It incorporates a Bit Error Rate (BER)-aware decoder that adapts to dynamic channel conditions and a Soft Quantization (SQ)-based encoder to learn compact representations. Building on this architecture, we introduce Feature-augmentation Learning, a novel training strategy that enhances offloading efficiency. To address encoder-decoder capability mismatches from asymmetric resources, we propose XAI-based Asymmetry Compensation to enhance decoding semantic fidelity. We conduct extensive experiments on STM32 using three models and six datasets across image classification and object detection tasks. Experimental results demonstrate that, under varying transmission error rates, SemanticNN significantly reduces feature transmission volume by 56.82-344.83x while maintaining superior inference accuracy.
Read the full abstract
Computer Vision
CrossMed: A Multimodal Cross-Task Benchmark for Compositional Generalization in Medical Imaging
Recent advances in multimodal large language models have enabled unified processing of visual and textual inputs, offering promising applications in general-purpose medical AI. However, their ability to generalize compositionally across unseen combinations of imaging modality, anatomy, and task type remains underexplored. We introduce CrossMed, a benchmark designed to evaluate compositional generalization (CG) in medical multimodal LLMs using a structured Modality-Anatomy-Task (MAT) schema. CrossMed reformulates four public datasets, CheXpert (X-ray classification), SIIM-ACR (X-ray segmentation), BraTS 2020 (MRI classification and segmentation), and MosMedData (CT classification) into a unified visual question answering (VQA) format, resulting in 20,200 multiple-choice QA instances. We evaluate two open-source multimodal LLMs, LLaVA-Vicuna-7B and Qwen2-VL-7B, on both Related and Unrelated MAT splits, as well as a zero-overlap setting where test triplets share no Modality, Anatomy, or Task with the training data. Models trained on Related splits achieve 83.2 percent classification accuracy and 0.75 segmentation cIoU, while performance drops significantly under Unrelated and zero-overlap conditions, demonstrating the benchmark difficulty. We also show cross-task transfer, where segmentation performance improves by 7 percent cIoU even when trained using classification-only data. Traditional models (ResNet-50 and U-Net) show modest gains, confirming the broad utility of the MAT framework, while multimodal LLMs uniquely excel at compositional generalization. CrossMed provides a rigorous testbed for evaluating zero-shot, cross-task, and modality-agnostic generalization in medical vision-language models.
Read the full abstract
Computer Vision
MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation
Automatic segmentation methods of polyps is crucial for assisting doctors in colorectal polyp screening and cancer diagnosis. Despite the progress made by existing methods, polyp segmentation faces several challenges: (1) small-sized polyps are prone to being missed during identification, (2) the boundaries between polyps and the surrounding environment are often ambiguous, (3) noise in colonoscopy images, caused by uneven lighting and other factors, affects segmentation results. To address these challenges, this paper introduces coupling gates as components in specific modules to filter noise and perform feature importance selection. Three modules are proposed: the coupling gates multiscale feature extraction (CGMFE) module, which effectively extracts local features and suppresses noise; the windows cross attention (WCAD) decoder module, which restores details after capturing the precise location of polyps; and the decoder feature aggregation (DFA) module, which progressively aggregates features, further extracts them, and performs feature importance selection to reduce the loss of small-sized polyps. Experimental results demonstrate that MPCGNet outperforms recent networks, with mDice scores 2.20% and 0.68% higher than the second-best network on the ETIS-LaribPolypDB and CVC-ColonDB datasets, respectively.
Read the full abstract
Computer Vision
Accelerating Controllable Generation via Hybrid-grained Cache
Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation computational requirements, resulting in generally low generation efficiency. To address this issue, we propose a Hybrid-Grained Cache (HGC) approach that reduces computational overhead by adopting cache strategies with different granularities at different computational stages. Specifically, (1) we use a coarse-grained cache (block-level) based on feature reuse to dynamically bypass redundant computations in encoder-decoder blocks between each step of model reasoning. (2) We design a fine-grained cache (prompt-level) that acts within a module, where the fine-grained cache reuses cross-attention maps within consecutive reasoning steps and extends them to the corresponding module computations of adjacent steps. These caches of different granularities can be seamlessly integrated into each computational link of the controllable generation process. We verify the effectiveness of HGC on four benchmark datasets, especially its advantages in balancing generation efficiency and visual quality. For example, on the COCO-Stuff segmentation benchmark, our HGC significantly reduces the computational cost (MACs) by 63% (from 18.22T to 6.70T), while keeping the loss of semantic fidelity (quantized performance degradation) within 1.5%.
Read the full abstract
Computer Vision
Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types
Artificial intelligence is revealing what medicine never intended to encode. Deep vision models, trained on chest X-rays, can now detect not only disease but also invisible traces of social inequality. In this study, we show that state-of-the-art architectures (DenseNet121, SwinV2-B, MedMamba) can predict a patient's health insurance type, a strong proxy for socioeconomic status, from normal chest X-rays with significant accuracy (AUC around 0.70 on MIMIC-CXR-JPG, 0.68 on CheXpert). The signal was unlikely contributed by demographic features by our machine learning study combining age, race, and sex labels to predict health insurance types; it also remains detectable when the model is trained exclusively on a single racial group. Patch-based occlusion reveals that the signal is diffuse rather than localized, embedded in the upper and mid-thoracic regions. This suggests that deep networks may be internalizing subtle traces of clinical environments, equipment differences, or care pathways; learning socioeconomic segregation itself. These findings challenge the assumption that medical images are neutral biological data. By uncovering how models perceive and exploit these hidden social signatures, this work reframes fairness in medical AI: the goal is no longer only to balance datasets or adjust thresholds, but to interrogate and disentangle the social fingerprints embedded in clinical data itself.
Read the full abstract
Computer Vision
EmbryoDiff: A Conditional Diffusion Framework with Multi-Focal Feature Fusion for Fine-Grained Embryo Developmental Stage Recognition
Identification of fine-grained embryo developmental stages during In Vitro Fertilization (IVF) is crucial for assessing embryo viability. Although recent deep learning methods have achieved promising accuracy, existing discriminative models fail to utilize the distributional prior of embryonic development to improve accuracy. Moreover, their reliance on single-focal information leads to incomplete embryonic representations, making them susceptible to feature ambiguity under cell occlusions. To address these limitations, we propose EmbryoDiff, a two-stage diffusion-based framework that formulates the task as a conditional sequence denoising process. Specifically, we first train and freeze a frame-level encoder to extract robust multi-focal features. In the second stage, we introduce a Multi-Focal Feature Fusion Strategy that aggregates information across focal planes to construct a 3D-aware morphological representation, effectively alleviating ambiguities arising from cell occlusions. Building on this fused representation, we derive complementary semantic and boundary cues and design a Hybrid Semantic-Boundary Condition Block to inject them into the diffusion-based denoising process, enabling accurate embryonic stage classification. Extensive experiments on two benchmark datasets show that our method achieves state-of-the-art results. Notably, with only a single denoising step, our model obtains the best average test performance, reaching 82.8% and 81.3% accuracy on the two datasets, respectively.
Read the full abstract
Computer Vision
AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning
Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality single-agent images, thus failing to evaluate MLLMs in more complex, egocentric collaborative scenarios, especially under real-world degraded perception conditions.To address these challenges, we introduce AirCopBench, the first comprehensive benchmark designed to evaluate MLLMs in embodied aerial collaborative perception under challenging perceptual conditions. AirCopBench includes 14.6k+ questions derived from both simulator and real-world data, spanning four key task dimensions: Scene Understanding, Object Understanding, Perception Assessment, and Collaborative Decision, across 14 task types. We construct the benchmark using data from challenging degraded-perception scenarios with annotated collaborative events, generating large-scale questions through model-, rule-, and human-based methods under rigorous quality control. Evaluations on 40 MLLMs show significant performance gaps in collaborative perception tasks, with the best model trailing humans by 24.38% on average and exhibiting inconsistent results across tasks. Fine-tuning experiments further confirm the feasibility of sim-to-real transfer in aerial collaborative perception and reasoning.
Read the full abstract
Computer Vision
SUPER Module for Detail-Sensitive and Cost-Efficient U-Net Variant Decoders
Skip-connected U-Net variants are widely used for dense inverse problems, yet their decoders commonly recover resolution through spatial upscaling, which can blur or distort fine structures. Wavelet transforms provide an explicit perfect-reconstruction path, but prior wavelet networks often couple this property to wavelet-specific architectures or fixed output representations. We propose Selectively Suppressed Perfect Reconstruction (SUPER), a wavelet-domain decoder formulation that replaces unstructured spatial refinement with bounded frequency suppression. In its idealized equal-channel form, SUPER reduces to exact reconstruction when the suppression term is zero; in practical U-Net decoders, it provides a projected-subspace reconstruction fallback with learnable task-specific suppression. The resulting SUPER Module is a structurally plug-in decoder block: it replaces the upsampling/refinement stage of an existing U-Net-like decoder, while leaving the encoder and task head unchanged. We evaluate SUPER on monocular depth estimation, thin-crack segmentation, and smartphone image denoising. On iDisc depth estimation, SUPER improves the host model's edge AUC from 26.59% to 34.45% while reducing decoder MACs from 12.69G to 4.36G. On FACS-Net crack segmentation, SUPER improves average IoU and the extreme 0-2px crack regime. On SIDD denoising, where high-frequency enhancement is less directly rewarded, SUPER preserves PSNR/SSIM while reducing decoder MACs by 66.6%. These results support SUPER as a practical wavelet-domain suppression module for improving the observed detail-cost trade-off of U-Net-like decoders.
Read the full abstract
Computer Vision
SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation
While diffusion-based T2I models have achieved remarkable image generation quality, they also enable easy creation of harmful content, raising social concerns and highlighting the need for safer generation. Existing inference-time guiding methods lack both adaptivity–adjusting guidance strength based on the prompt–and selectivity–targeting only unsafe regions of the image. Our method, SP-Guard, addresses these limitations by estimating prompt harmfulness and applying a selective guidance mask to guide only unsafe areas. Experiments show that SP-Guard generates safer images than existing methods while minimizing unintended content alteration. Beyond improving safety, our findings highlight the importance of transparency and controllability in image generation.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overlook robustness against adversarial attacks. Although vanilla adversarial training (VAT) improves the robustness of deep neural networks, it has little effect on UDA. This paper focuses on answering three key questions: 1) Why does VAT, known for its defensive effectiveness, fail in the UDA paradigm? 2) What is the generalization bound theory under attacks and how does it evolve from classical UDA theory? 3) How can we implement a robustification training procedure without complex modifications? Specifically, we explore and reveal the inherent entanglement challenge in general UDA+VAT paradigm, and propose an unsupervised robust domain adaptation (URDA) paradigm. We further derive the generalization bound theory of the URDA paradigm so that it can resist adversarial noise and domain shift. To the best of our knowledge, this is the first time to establish the URDA paradigm and theory. We further introduce a simple, novel yet effective URDA algorithm called Disentangled Adversarial Robustness Training (DART), a two-step training procedure that ensures both transferability and robustness. DART first pre-trains an arbitrary UDA model, and then applies an instantaneous robustification post-training step via disentangled distillation.Experiments on four benchmark datasets with/without attacks show that DART effectively enhances robustness while maintaining domain adaptability, and validate the URDA paradigm and theory.
Read the full abstract
Computer Vision
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a deficit in contextualized visual experience during prolonged generation. Drawing inspiration from human cognitive memory theory, which distinguishes short-term visually-dominant memory and long-term semantically-dominant memory, we propose VisMem, a cognitively-aligned framework that equips VLMs with dynamic latent vision memories, a short-term module for fine-grained perceptual retention and a long-term module for abstract semantic consolidation. These memories are seamlessly invoked during inference, allowing VLMs to maintain both perceptual fidelity and semantic consistency across thinking and generation. Extensive experiments across diverse visual benchmarks for understanding, reasoning, and generation reveal that VisMem delivers a significant average performance boost of 11.0% relative to the vanilla model and outperforms all counterparts, establishing a new paradigm for latent-space memory enhancement. The code will be available: https://github.com/YU-deep/VisMem.git.
Read the full abstract
Computer Vision
Draft and Refine with Visual Experts
While recent Large Vision-Language Models (LVLMs) exhibit strong multimodal reasoning abilities, they often produce ungrounded or hallucinated responses because they rely too heavily on linguistic priors instead of visual evidence. This limitation highlights the absence of a quantitative measure of how much these models actually use visual information during reasoning. We propose Draft and Refine (DnR), an agent framework driven by a question-conditioned utilization metric. The metric quantifies the model's reliance on visual evidence by first constructing a query-conditioned relevance map to localize question-specific cues and then measuring dependence through relevance-guided probabilistic masking. Guided by this metric, the DnR agent refines its initial draft using targeted feedback from external visual experts. Each expert's output (such as boxes or masks) is rendered as visual cues on the image, and the model is re-queried to select the response that yields the largest improvement in utilization. This process strengthens visual grounding without retraining or architectural changes. Experiments across VQA and captioning benchmarks show consistent accuracy gains and reduced hallucination, demonstrating that measuring visual utilization provides a principled path toward more interpretable and evidence-driven multimodal agent systems. Code is available at https://github.com/EavnJeong/Draft-and-Refine-with-Visual-Experts.
Read the full abstract
Computer Vision
MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis
Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology, achieving strong diagnostic performance through patch-level feature aggregation. However, existing MIL methods face critical limitations: (1) they rely on attention mechanisms that lack causal interpretability, and (2) they fail to integrate patient demographics (age, gender, race), leading to fairness concerns across diverse populations. These shortcomings hinder clinical translation, where algorithmic bias can exacerbate health disparities. We introduce MeCaMIL, a causality-aware MIL framework that explicitly models demographic confounders through structured causal graphs. Unlike prior approaches treating demographics as auxiliary features, MeCaMIL employs principled causal inference – leveraging do-calculus and collider structures – to disentangle disease-relevant signals from spurious demographic correlations. Extensive evaluation on three benchmarks demonstrates state-of-the-art performance across CAMELYON16 (ACC/AUC/F1: 0.939/0.983/0.946), TCGA-Lung (0.935/0.979/0.931), and TCGA-Multi (0.977/0.993/0.970, five cancer types). Critically, MeCaMIL achieves superior fairness – demographic disparity variance drops by over 65% relative reduction on average across attributes, with notable improvements for underserved populations. The framework generalizes to survival prediction (mean C-index: 0.653, +0.017 over best baseline across five cancer types). Ablation studies confirm causal graph structure is essential – alternative designs yield 0.048 lower accuracy and 4.2x times worse fairness. These results establish MeCaMIL as a principled framework for fair, interpretable, and clinically actionable AI in digital pathology. Code will be released upon acceptance.
Read the full abstract
Computer Vision
EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation
Emotion plays a pivotal role in video-based expression, but existing video generation systems predominantly focus on low-level visual metrics while neglecting affective dimensions. Although emotion analysis has made progress in the visual domain, the video community lacks dedicated resources to bridge emotion understanding with generative tasks, particularly for stylized and non-realistic contexts. To address this gap, we introduce EmoVid, the first multimodal, emotion-annotated video dataset specifically designed for creative media, which includes cartoon animations, movie clips, and animated stickers. Each video is annotated with emotion labels, visual attributes (brightness, colorfulness, hue), and text captions. Through systematic analysis, we uncover spatial and temporal patterns linking visual features to emotional perceptions across diverse video forms. Building on these insights, we develop an emotion-conditioned video generation technique by fine-tuning the Wan2.1 model. The results show a significant improvement in both quantitative metrics and the visual quality of generated videos for text-to-video and image-to-video tasks. EmoVid establishes a new benchmark for affective video computing. Our work not only offers valuable insights into visual emotion analysis in artistically styled videos, but also provides practical methods for enhancing emotional expression in video generation.
Read the full abstract
Computer Vision
PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing Modalities
Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities are missing or unavailable. This degradation primarily stems from inconsistent representation learning between complete multimodal data and incomplete modality scenarios. Existing approaches typically address missing modalities through relatively simplistic generation methods, yet these approaches fail to adequately preserve cross-modal consistency, leading to suboptimal performance. To overcome this limitation, we propose a novel multimodal framework named PROMISE, a PROMpting-Attentive HIerarchical ContraStive LEarning approach designed explicitly for robust cross-modal representation under conditions of missing modalities. Specifically, PROMISE innovatively incorporates multimodal prompt learning into a hierarchical contrastive learning framework, equipped with a specially designed prompt-attention mechanism. This mechanism dynamically generates robust and consistent representations for scenarios where particular modalities are absent, thereby effectively bridging the representational gap between complete and incomplete data. Extensive experiments conducted on benchmark datasets, along with comprehensive ablation studies, clearly demonstrate the superior performance of PROMISE compared to current state-of-the-art multimodal methods.
Read the full abstract
Computer Vision
CLUE: Controllable Latent space of Unprompted Embeddings for Diversity Management in Text-to-Image Synthesis
Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the integration of additional data modalities during training. Although these methods have shown promising results in general domains, they face limitations when applied to specialized fields such as medicine, where only limited types and insufficient amounts of data are available. We present CLUE (Controllable Latent space of Unprompted Embeddings), a generative model framework that achieves diverse generation while maintaining stability through fixed-format prompts without requiring any additional data. Based on the Stable Diffusion architecture, CLUE employs a Style Encoder that processes images and prompts to generate style embeddings, which are subsequently fed into a new second attention layer of the U-Net architecture. Through Kullback-Leibler divergence, the latent space achieves continuous representation of image features within Gaussian regions, independent of prompts. Performance was assessed on otitis media dataset. CLUE reduced FID to 9.30 (vs. 46.81) and improved recall to 70.29% (vs. 49.60%). A classifier trained on synthetic-only data at 1000% scale achieved an F1 score of 83.21% (vs. 73.83%). Combining synthetic data with equal amounts of real data achieved an F1 score of 94.76%, higher than when using only real data. On an external dataset, synthetic-only training achieved an F1 score of 76.77% (vs. 60.61%) at 1000% scale. The combined approach achieved an F1 score of 85.78%, higher than when using only the internal dataset. These results demonstrate that CLUE enables diverse yet stable image generation from limited datasets and serves as an effective data augmentation method for domain-specific applications.