Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 15 November
Deepfakes are major threats to the integrity of digital media. We propose DeiTFake, a DeiT-based transformer and a novel two-stage progressive training strategy with increasing augmentation complexity. The approach applies an initial transfer-learning phase with standard augmentations followed by a fine-tuning phase using advanced affine and deepfake-specific augmentations. DeiT's knowledge distillation model captures subtle manipulation artifacts, increasing robustness of the detection model. Trained on the OpenForensics dataset (190,335 images), DeiTFake achieves 98.71% accuracy after stage one and 99.22% accuracy with an AUROC of 0.9997, after stage two, outperforming the latest OpenForensics baselines. We analyze augmentation impact and training schedules, and provide practical benchmarks for facial deepfake detection.
Computer Vision
DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging
Medical images exhibit latent anatomical groupings, such as organs, tissues, and pathological regions, that standard Vision Transformers (ViTs) fail to exploit. While recent work like SBM-Transformer attempts to incorporate such structures through stochastic binary masking, they suffer from non-differentiability, training instability, and the inability to model complex community structure. We present DCMM-Transformer, a novel ViT architecture for medical image analysis that incorporates a Degree-Corrected Mixed-Membership (DCMM) model as an additive bias in self-attention. Unlike prior approaches that rely on multiplicative masking and binary sampling, our method introduces community structure and degree heterogeneity in a fully differentiable and interpretable manner. Comprehensive experiments across diverse medical imaging datasets, including brain, chest, breast, and ocular modalities, demonstrate the superior performance and generalizability of the proposed approach. Furthermore, the learned group structure and structured attention modulation substantially enhance interpretability by yielding attention maps that are anatomically meaningful and semantically coherent.
Read the full abstract
Computer Vision · Cross-listed from cs.CR
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks–most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally intensive: they employ surrogate student models and simulated distillation to guarantee transferability, and construct triggers similar to universal adversarial perturbations (UAPs), which being not stealthy in magnitude, inherently exhibit strong adversarial behavior. This work questions whether such complexity is necessary and constructs stealthy "weak" triggers–imperceptible perturbations that have negligible adversarial effect. We propose BackWeak, a simple, surrogate-free attack paradigm. BackWeak shows that a powerful backdoor can be implanted by simply fine-tuning a benign teacher with a weak trigger using a very small learning rate. We demonstrate that this delicate fine-tuning is sufficient to embed a backdoor that reliably transfers to diverse student architectures during a victim's standard distillation process, yielding high attack success rates. Extensive empirical evaluations on multiple datasets, model architectures, and KD methods show that BackWeak is efficient, simpler, and often more stealthy than previous elaborate approaches. This work calls on researchers studying KD backdoor attacks to pay particular attention to the trigger's potential adversarial characteristics.
Read the full abstract
Computer Vision
FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically distributed) data poses an inevitable challenge that hinders the use of FL. In this work, we address the issue of non-IID histopathological images with feature distribution shifts from an intuitive perspective that has only received limited attention. Specifically, we address this issue from the perspective of data distribution by solely adjusting the data distributions of all clients. Building on the success of diffusion models in fitting data distributions and leveraging stain separation to extract the pivotal features that are closely related to the non-IID properties of histopathological images, we propose a Federated Stain Distribution Alignment (FedSDA) method. FedSDA aligns the stain distribution of each client with a target distribution in an FL framework to mitigate distribution shifts among clients. Furthermore, considering that training diffusion models on raw data in FL has been shown to be susceptible to privacy leakage risks, we circumvent this problem while still effectively achieving alignment. Extensive experimental results show that FedSDA is not only effective in improving baselines that focus on mitigating disparities across clients' model updates but also outperforms baselines that address the non-IID data issues from the perspective of data distribution. We show that FedSDA provides valuable and practical insights for the computational pathology community.
Read the full abstract
Computer Vision
SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images
Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details. This limitation stems from the inherent lack of high-frequency information in LR inputs. To address this, we propose SRSplat, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views. Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues. We first construct a scene-specific reference gallery, generated for each scene using Multimodal Large Language Models (MLLMs) and diffusion models. To integrate this external information, we introduce the Reference-Guided Feature Enhancement (RGFE) module, which aligns and fuses features from the LR input images and their reference twin image. Subsequently, we train a decoder to predict the Gaussian primitives using the multi-view fused feature obtained from RGFE. To further refine predicted Gaussian primitives, we introduce Texture-Aware Density Control (TADC), which adaptively adjusts Gaussian density based on the internal texture richness of the LR inputs. Extensive experiments demonstrate that our SRSplat outperforms existing methods on various datasets, including RealEstate10K, ACID, and DTU, and exhibits strong cross-dataset and cross-resolution generalization capabilities.
Read the full abstract
Computer Vision · Cross-listed from cs.AR
Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they suffer from substantial inference delay due to self-attention. While prior studies have focused on reducing redundant computations in self-attention, they often overlook the inherent spatio-temporal correlations in video streams and directly leverage sparsity patterns from large language models to reduce attention computations. In this work, we take a principled approach to accelerate self-attention in vDiTs by leveraging the spatio-temporal correlations in the latent space. We show that the attention patterns within vDiT are primarily due to the dominant spatial and temporal correlations at the token channel level. Based on this insight, we propose a lightweight and adaptive reuse strategy that approximates attention computations by reusing partial attention scores of spatially or temporally correlated tokens along individual channels. We demonstrate that our method achieves significantly higher computational savings (85%) compared to state-of-the-art techniques over 4 vDiTs, while preserving almost identical video quality ($<$0.06% loss on VBench).
Read the full abstract
Computer Vision
Calibrated Multimodal Representation Learning with Missing Modalities
Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities to be present for a common instance, making it challenging to utilize prevalent datasets with missing modalities. We provide theoretical insights into this issue from an anchor shift perspective. Observed modalities are aligned with a local anchor that deviates from the optimal one when all modalities are present, resulting in an inevitable shift. To address this, we propose CalMRL to calibrate incomplete alignments caused by missing modalities. CalMRL leverages the priors and the inherent connections among modalities to model the imputation for the missing ones at the representation level. To resolve the optimization dilemma, we employ a bi-step learning method with the closed-form solution of the posterior distribution of shared latents. We validate its mitigation of anchor shift and convergence with theoretical guidance. By equipping the calibrated alignment with the existing advanced method, we offer new flexibility to absorb data with missing modalities, which is originally unattainable. Extensive experiments demonstrate the superiority of CalMRL. The code is released at https://github.com/Xiaohao-Liu/CalMRL.
Read the full abstract
Computer Vision
Improved Masked Image Generation with Knowledge-Augmented Token Representations
Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual token sequences. However, directly learning such semantic dependencies from data is challenging because the individual tokens lack clear semantic meanings, and these sequences are usually long. To address this limitation, we propose a novel Knowledge-Augmented Masked Image Generation framework, named KA-MIG, which introduces explicit knowledge of token-level semantic dependencies (i.e., extracted from the training data) as priors to learn richer representations for improving performance. In particular, we explore and identify three types of advantageous token knowledge graphs, including two positive and one negative graphs (i.e., the co-occurrence graph, the semantic similarity graph, and the position-token incompatibility graph). Based on three prior knowledge graphs, we design a graph-aware encoder to learn token and position-aware representations. After that, a lightweight fusion mechanism is introduced to integrate these enriched representations into the existing MIG methods. Resorting to such prior knowledge, our method effectively enhances the model's ability to capture semantic dependencies, leading to improved generation quality. Experimental results demonstrate that our method improves upon existing MIG for class-conditional image generation on ImageNet.
Read the full abstract
Computer Vision
VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation
Estimating the 3D poses of hands and objects from a single RGB image is a fundamental yet challenging problem, with broad applications in augmented reality and human-computer interaction. Existing methods largely rely on visual cues alone, often producing results that violate physical constraints such as interpenetration or non-contact. Recent efforts to incorporate physics reasoning typically depend on post-optimization or non-differentiable physics engines, which compromise visual consistency and end-to-end trainability. To overcome these limitations, we propose a novel framework that jointly integrates visual and physical cues for hand-object pose estimation. This integration is achieved through two key ideas: 1) joint visual-physical cue learning: The model is trained to extract 2D visual cues and 3D physical cues, thereby enabling more comprehensive representation learning for hand-object interactions; 2) candidate pose aggregation: A novel refinement process that aggregates multiple diffusion-generated candidate poses by leveraging both visual and physical predictions, yielding a final estimate that is visually consistent and physically plausible. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art approaches in both pose accuracy and physical plausibility.
Read the full abstract
Computer Vision
GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture the global context and complex event relationships necessary for deep video reasoning. To address this, we introduce GCAgent, a novel Global-Context-Aware Agent framework that achieves comprehensive long-video understanding. Our core innovation is the Schematic and Narrative Episodic Memory. This memory structurally models events and their causal and temporal relations into a concise, organized context, fundamentally resolving the long-term dependency problem. Operating in a multi-stage Perception-Action-Reflection cycle, our GCAgent utilizes a Memory Manager to retrieve relevant episodic context for robust, context-aware inference. Extensive experiments confirm that GCAgent significantly enhances long-video understanding, achieving up to 23.5% accuracy improvement on the Video-MME Long split over a strong MLLM baseline. Furthermore, our framework establishes state-of-the-art performance among comparable 7B-scale MLLMs, achieving 73.4% accuracy on the Long split and the highest overall average (71.9%) on the Video-MME benchmark, validating our agent-based reasoning paradigm and structured memory for cognitively-inspired long-video understanding.
Read the full abstract
Computer Vision
Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark
Accurate point tracking in surgical environments remains challenging due to complex visual conditions, including smoke occlusion, specular reflections, and tissue deformation. While existing surgical tracking datasets provide coordinate information, they lack the semantic context necessary to understand tracking failure mechanisms. We introduce VL-SurgPT, the first large-scale multimodal dataset that bridges visual tracking with textual descriptions of point status in surgical scenes. The dataset comprises 908 in vivo video clips, including 754 for tissue tracking (17,171 annotated points across five challenging scenarios) and 154 for instrument tracking (covering seven instrument types with detailed keypoint annotations). We establish comprehensive benchmarks using eight state-of-the-art tracking methods and propose TG-SurgPT, a text-guided tracking approach that leverages semantic descriptions to improve robustness in visually challenging conditions. Experimental results demonstrate that incorporating point status information significantly improves tracking accuracy and reliability, particularly in adverse visual scenarios where conventional vision-only methods struggle. By bridging visual and linguistic modalities, VL-SurgPT enables the development of context-aware tracking systems crucial for advancing computer-assisted surgery applications that can maintain performance even under challenging intraoperative conditions.
Read the full abstract
Computer Vision
Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging
Lensless imaging reconstructs scenes from highly multiplexed measurements, resulting in a severely ill-posed inverse problem. In this work, we identify a fundamental trade-off between measurement consistency, perceptual quality, and inference speed across lensless reconstruction paradigms. Traditional methods favor consistency but produce perceptually degraded results, supervised approaches achieve high-quality reconstructions with fast inference but may violate physical constraints, and diffusion-prior methods achieve high perceptual quality and consistency–particularly when structured constraints such as range-null decomposition are used–but remain slow due to iterative sampling. Motivated by this observation, we propose Null-Space Diffusion Distillation (NSDD), a single-pass reconstruction model that distills structured diffusion-prior inference into an efficient feed-forward network. NSDD learns to produce high-quality reconstructions that preserve measurement consistency while avoiding costly iterative sampling. Experimental results demonstrate that NSDD achieves perceptual quality and consistency competitive with diffusion-prior methods, while providing significantly faster inference and offering a favorable balance across all three objectives. Furthermore, ablation experiments show that distilling the range–null decomposition improves reconstruction quality and robustness over unstructured full-reconstruction distillation, including on unseen real scenes. These results highlight the potential of structure-aware distillation for efficient lensless imaging. Code is available at github.com/JRCSAVSN/NullSpaceDiffusionDistillation.
Read the full abstract
Computer Vision
LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension
Existing Weakly-Supervised Referring Expression Comprehension (WREC) methods, while effective, are fundamentally limited by a one-to-one mapping assumption, hindering their ability to handle expressions corresponding to zero or multiple targets in realistic scenarios. To bridge this gap, we introduce the Weakly-Supervised Generalized Referring Expression Comprehension task (WGREC), a more practical paradigm that handles expressions with variable numbers of referents. However, extending WREC to WGREC presents two fundamental challenges: supervisory signal ambiguity, where weak image-level supervision is insufficient for training a model to infer the correct number and identity of referents, and semantic representation collapse, where standard Euclidean similarity forces hierarchically-related concepts into non-discriminative clusters, blurring categorical boundaries. To tackle these challenges, we propose a novel WGREC framework named Linguistic Instance-Split Hyperbolic-Euclidean (LIHE), which operates in two stages. The first stage, Referential Decoupling, predicts the number of target objects and decomposes the complex expression into simpler sub-expressions. The second stage, Referent Grounding, then localizes these sub-expressions using HEMix, our innovative hybrid similarity module that synergistically combines the precise alignment capabilities of Euclidean proximity with the hierarchical modeling strengths of hyperbolic geometry. This hybrid approach effectively prevents semantic collapse while preserving fine-grained distinctions between related concepts. Extensive experiments demonstrate LIHE establishes the first effective weakly supervised WGREC baseline on gRefCOCO and Ref-ZOM, while HEMix achieves consistent improvements on standard REC benchmarks, improving IoU@0.5 by up to 2.5%. The code is available at https://anonymous.4open.science/r/LIHE.
Read the full abstract
Computer Vision
Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis
Traffic safety analysis at signalized intersections is essential for reducing vehicle and pedestrian collisions, yet traditional crash-based studies are limited by data sparsity and reporting latency. This paper presents a multi-camera computer vision framework for real-time safety assessment through Post-Encroachment Time (PET) computation, demonstrated at the intersection of H Street and Broadway in Chula Vista, California. Four synchronized cameras provide continuous visual coverage, with frames processed on NVIDIA Jetson AGX Xavier edge devices using YOLOv11 segmentation for vehicle detection. Detected vehicle polygons are transformed into a unified bird's-eye map via homography, enabling alignment across overlapping camera views. A pixel-level PET algorithm tracks temporal occupancy at each spatial location by measuring the time between successive vehicle passages, enabling fine-grained hazard visualization through dynamic heatmaps with 3.3 sq-cm spatial resolution. Timestamped vehicle trajectories and PET data are stored in an SQL database for longitudinal analysis. Results across multiple time intervals demonstrate the framework's ability to identify high-risk regions with sub-second temporal sensitivity and real-time edge throughput, generating 800 x 800 logarithmic heatmaps at an average of 2.68 FPS. This paper validates decentralized vision-based PET analysis for intelligent transportation systems and presents a scalable methodology for high-resolution, real-time intersection safety evaluation.
Read the full abstract
Computer Vision · Cross-listed from cs.AI
Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models
AI tools in pathology have improved screening throughput, standardized quantification, and revealed prognostic patterns that inform treatment. However, adoption remains limited because most systems still lack the human-readable reasoning needed to audit decisions and prevent errors. We present RECAP-PATH, an interpretable framework that establishes a self-learning paradigm, shifting off-the-shelf multimodal large language models from passive pattern recognition to evidence-linked diagnostic reasoning. At its core is a two-phase learning process that autonomously derives diagnostic criteria: diversification expands pathology-style explanations, while optimization refines them for accuracy. This self-learning approach requires only small labeled sets and no white-box access or weight updates to generate cancer diagnoses. Evaluated on breast and prostate datasets, RECAP-PATH produced rationales aligned with expert assessment and delivered substantial gains in diagnostic accuracy over baselines. By uniting visual understanding with reasoning, RECAP-PATH provides clinically trustworthy AI and demonstrates a generalizable path toward evidence-linked interpretation.
Read the full abstract
Computer Vision
Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy
Deep learning is transforming microscopy, yet models often fail when applied to images from new instruments or acquisition settings. Conventional adversarial domain adaptation (ADDA) retrains entire networks, often disrupting learned semantic representations. Here, we overturn this paradigm by showing that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer. Building on this principle, we introduce Subnetwork Image Translation ADDA with automatic depth selection (SIT-ADDA-Auto), a self-configuring framework that integrates shallow-layer adversarial alignment with predictive uncertainty to automatically select adaptation depth without target labels. We demonstrate robustness via multi-metric evaluation, blinded expert assessment, and uncertainty-depth ablations. Across exposure and illumination shifts, cross-instrument transfer, and multiple stains, SIT-ADDA improves reconstruction and downstream segmentation over full-encoder adaptation and non-adversarial baselines, with reduced drift of semantic features. Our results provide a design rule for label-free adaptation in microscopy and a recipe for field settings; the code is publicly available.
Read the full abstract
Computer Vision
LithoSeg: A Coarse-to-Fine Framework for High-Precision Lithography Segmentation
Accurate segmentation and measurement of lithography scanning electron microscope (SEM) images are crucial for ensuring precise process control, optimizing device performance, and advancing semiconductor manufacturing yield. Lithography segmentation requires pixel-level delineation of groove contours and consistent performance across diverse pattern geometries and process window. However, existing methods often lack the necessary precision and robustness, limiting their practical applicability. To overcome this challenge, we propose LithoSeg, a coarse-to-fine network tailored for lithography segmentation. In the coarse stage, we introduce a Human-in-the-Loop Bootstrapping scheme for the Segment Anything Model (SAM) to attain robustness with minimal supervision. In the subsequent fine stage, we recast 2D segmentation as 1D regression problem by sampling groove-normal profiles using the coarse mask and performing point-wise refinement with a lightweight MLP. LithoSeg outperforms previous approaches in both segmentation accuracy and metrology precision while requiring less supervision, offering promising prospects for real-world applications.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Selecting Fine-Tuning Examples by Quizzing VLMs
A challenge in fine-tuning text-to-image diffusion models for specific topics is to select good examples. Fine-tuning from image sets of varying quality, such as Wikipedia Commons, will often produce poor output. However, training images that do exemplify the target concept (e.g., a female Mountain Bluebird) help ensure that the generated images are similarly representative (e.g., have the prototypical blue-wings and gray chest). In this work, we propose QZLoRA, a framework to select images for low-rank adaptation (LoRA). The approach leverages QuizRank, a method to automatically rank images by treating them as an `educational intervention' and `quizzing' a VLM. We demonstrate that QZLoRA can produce better aligned, photorealistic images with fewer samples. We also show that these fine-tuned models can produce stylized that are similarly representative (i.e., illustrations). Our results highlight the promise of combining automated visual reasoning with parameter-efficient fine-tuning for topic-adaptive generative modeling.
Read the full abstract
Computer Vision
Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
Despite their wide application, the vulnerabilities of deep neural networks raise societal concerns. Among them, transformation-based attacks have demonstrated notable success in transfer attacks. However, existing attacks suffer from blind spots in parameter optimization, limiting their full potential. Specifically, (1) prior work generally considers low-iteration settings, yet attacks perform quite differently at higher iterations, so characterizing overall performance based only on low-iteration results is misleading. (2) Existing attacks use uniform parameters for different surrogate models, iterations, and tasks, which greatly impairs transferability. (3) Traditional transformation parameter optimization relies on grid search. For n parameters with m steps each, the complexity is O(mn). Large computational overhead limits further optimization of parameters. To address these limitations, we conduct an empirical study with various transformations as baselines, revealing three dynamic patterns of transferability with respect to parameter strength. We further propose a novel Concentric Decay Model (CDM) to effectively explain these patterns. Building on these insights, we propose an efficient Dynamic Parameter Optimization (DPO) based on the rise-then-fall pattern, reducing the complexity to O(nlogm). Comprehensive experiments on existing transformation-based attacks across different surrogate models, iterations, and tasks demonstrate that our DPO can significantly improve transferability.
Read the full abstract
Computer Vision
BeyondFacial: Identity-Preserving Personalized Generation Beyond Facial Close-ups
Identity-Preserving Personalized Generation (IPPG) has advanced film production and artistic creation, yet existing approaches overemphasize facial regions, resulting in outputs dominated by facial close-ups.These methods suffer from weak visual narrativity and poor semantic consistency under complex text prompts, with the core limitation rooted in identity (ID) feature embeddings undermining the semantic expressiveness of generative models. To address these issues, this paper presents an IPPG method that breaks the constraint of facial close-ups, achieving synergistic optimization of identity fidelity and scene semantic creation. Specifically, we design a Dual-Line Inference (DLI) pipeline with identity-semantic separation, resolving the representation conflict between ID and semantics inherent in traditional single-path architectures. Further, we propose an Identity Adaptive Fusion (IdAF) strategy that defers ID-semantic fusion to the noise prediction stage, integrating adaptive attention fusion and noise decision masking to avoid ID embedding interference on semantics without manual masking. Finally, an Identity Aggregation Prepending (IdAP) module is introduced to aggregate ID information and replace random initializations, further enhancing identity preservation. Experimental results validate that our method achieves stable and effective performance in IPPG tasks beyond facial close-ups, enabling efficient generation without manual masking or fine-tuning. As a plug-and-play component, it can be rapidly deployed in existing IPPG frameworks, addressing the over-reliance on facial close-ups, facilitating film-level character-scene creation, and providing richer personalized generation capabilities for related domains.
Read the full abstract
Computer Vision
From Classification to Cross-Modal Understanding: Leveraging Vision-Language Models for Fine-Grained Renal Pathology
Fine-grained glomerular subtyping is essential for kidney biopsy interpretation, yet it presents a harder setting than the broad organ- or disease-level recognition tasks commonly used in vision-language model (VLM) evaluation. In this task, all categories arise within the same renal microanatomic unit, and clinically meaningful subtypes often differ by subtle, overlapping, and continuum-like morphological cues. Clinically valuable labels are also scarce, making fully supervised image-only paradigms difficult to translate to practice. Although VLMs are promising for data-efficient pathology learning, it remains unclear how their cross-modal representations should be adapted and evaluated for such within-structure discrimination under realistic few-shot constraints. To our knowledge, this study establishes the first fine-grained renal pathology benchmark for few-shot VLM adaptation and systematically examines how supervision level, model design, and adaptation strategy shape both classification performance and multimodal representation structure. Beyond accuracy, AUC, and F1, we assess image-text alignment, positive-negative similarity separation, embedding geometry, and calibration (ECE), asking when performance gains reflect more reliable cross-modal understanding. Across renal pathology cohorts, additional supervision consistently improves discrimination, but reliable adaptation is not explained by alignment alone; stronger performance is associated with larger class separation, more coherent embedding organization, and better awareness of confidence-related failure modes under domain variation. Within this retrospective two-cohort evaluation, these findings move assessment beyond coarse classification and accuracy alone and provide comparative evidence to inform model selection and future translational validation. Code: https://github.com/ddrrnn123/glo-vlms
Read the full abstract
Computer Vision
Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs
This study presents a comparative analysis of three U-Net-based architectures for semantic segmentation of rock art petroglyphs from Brazilian archaeological sites. The investigated architectures were: (1) BEGL-UNet with Border-Enhanced Gaussian Loss function; (2) Attention-Residual BEGL-UNet, incorporating residual blocks and gated attention mechanisms; and (3) Spatial Channel Attention BEGL-UNet, which employs spatial-channel attention modules based on Convolutional Block Attention Module. All implementations employed the BEGL loss function combining binary cross-entropy with Gaussian edge enhancement. Experiments were conducted on images from the Poço da Bebidinha Archaeological Complex, Piauí, Brazil, using 5-fold cross-validation. Among the architectures, Attention-Residual BEGL-UNet achieved the best overall performance with Dice Score of 0.710, validation loss of 0.067, and highest recall of 0.854. Spatial Channel Attention BEGL-UNet obtained comparable performance with DSC of 0.707 and recall of 0.857. The baseline BEGL-UNet registered DSC of 0.690. These results demonstrate the effectiveness of attention mechanisms for archaeological heritage digital preservation, with Dice Score improvements of 2.5-2.9% over the baseline.
Read the full abstract
Computer Vision
Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing
Recent advances in text-to-image generation have produced strong single-shot models, yet no individual system reliably executes the long, compositional prompts typical of creative workflows. We introduce Image-POSER, a reflective reinforcement learning framework that (i) orchestrates a diverse registry of pretrained text-to-image and image-to-image experts, (ii) handles long-form prompts end-to-end through dynamic task decomposition, and (iii) supervises alignment at each step via structured feedback from a vision-language model critic. By casting image synthesis and editing as a Markov Decision Process, we learn non-trivial expert pipelines that adaptively combine strengths across models. Experiments show that Image-POSER outperforms baselines, including frontier models, across industry-standard and custom benchmarks in alignment, fidelity, and aesthetics, and is consistently preferred in human evaluations. These results highlight that reinforcement learning can endow AI systems with the capacity to autonomously decompose, reorder, and combine visual models, moving towards general-purpose visual assistants.
Read the full abstract
Friday 14 November
Computer Vision
SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control
Traditional text-to-motion frameworks often lack precise control, and existing approaches based on joint keyframe locations provide only positional guidance, making it challenging and unintuitive to specify body part orientations and motion timing. To address these limitations, we introduce the Salient Orientation Symbolic (SOS) script, a programmable symbolic framework for specifying body part orientations and motion timing at keyframes. We further propose an automatic SOS extraction pipeline that employs temporally-constrained agglomerative clustering for frame saliency detection and a Saliency-based Masking Scheme (SMS) to generate sparse, interpretable SOS scripts directly from motion data. Moreover, we present the SOSControl framework, which treats the available orientation symbols in the sparse SOS script as salient and prioritizes satisfying these constraints during motion generation. By incorporating SMS-based data augmentation and gradient-based iterative optimization, the framework enhances alignment with user-specified constraints. Additionally, it employs a ControlNet-based ACTOR-PAE Decoder to ensure smooth and natural motion outputs. Extensive experiments demonstrate that the SOS extraction pipeline generates human-interpretable scripts with symbolic annotations at salient keyframes, while the SOSControl framework outperforms existing baselines in motion quality, controllability, and generalizability with respect to motion timing and body part orientation control.
Read the full abstract
Computer Vision
Closing the Gap: Data-Centric Fine-Tuning of Vision Language Models for the Standardized Exam Questions
Multimodal reasoning has become a cornerstone of modern AI research. Standardized exam questions offer a uniquely rigorous testbed for such reasoning, providing structured visual contexts and verifiable answers. While recent progress has largely focused on algorithmic advances such as reinforcement learning (e.g., GRPO, DPO), the data centric foundations of vision language reasoning remain less explored. We show that supervised fine-tuning (SFT) with high-quality data can rival proprietary approaches. To this end, we compile a 161.4 million token multimodal dataset combining textbook question-solution pairs, curriculum aligned diagrams, and contextual materials, and fine-tune Qwen-2.5VL-32B using an optimized reasoning syntax (QMSA). The resulting model achieves 78.6% accuracy, only 1.0% below Gemini 2.0 Flash, on our newly released benchmark YKSUniform, which standardizes 1,854 multimodal exam questions across 309 curriculum topics. Our results reveal that data composition and representational syntax play a decisive role in multimodal reasoning. This work establishes a data centric framework for advancing open weight vision language models, demonstrating that carefully curated and curriculum-grounded multimodal data can elevate supervised fine-tuning to near state-of-the-art performance.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
VISTAv2: World Imagination for Indoor Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) requires agents to follow language instructions while acting in continuous real-world spaces. Prior image imagination based VLN work shows benefits for discrete panoramas but lacks online, action-conditioned predictions and does not produce explicit planning values; moreover, many methods replace the planner with long-horizon objectives that are brittle and slow. To bridge this gap, we propose VISTAv2, a generative world model that rolls out egocentric future views conditioned on past observations, candidate action sequences, and instructions, and projects them into an online value map for planning. Unlike prior approaches, VISTAv2 does not replace the planner. The online value map is fused at score level with the base objective, providing reachability and risk-aware guidance. Concretely, we employ an action-aware Conditional Diffusion Transformer video predictor to synthesize short-horizon futures, align them with the natural language instruction via a vision-language scorer, and fuse multiple rollouts in a differentiable imagination-to-value head to output an imagined egocentric value map. For efficiency, rollouts occur in VAE latent space with a distilled sampler and sparse decoding, enabling inference on a single consumer GPU. Evaluated on MP3D and RoboTHOR, VISTAv2 improves over strong baselines, and ablations show that action-conditioned imagination, instruction-guided value fusion, and the online value-map planner are all critical, suggesting that VISTAv2 offers a practical and interpretable route to robust VLN.
Read the full abstract
Computer Vision · Cross-listed from cs.NE
Temporal-adaptive Weight Quantization for Spiking Neural Networks
Weight quantization in spiking neural networks (SNNs) could further reduce energy consumption. However, quantizing weights without sacrificing accuracy remains challenging. In this study, inspired by astrocyte-mediated synaptic modulation in the biological nervous systems, we propose Temporal-adaptive Weight Quantization (TaWQ), which incorporates weight quantization with temporal dynamics to adaptively allocate ultra-low-bit weights along the temporal dimension. Extensive experiments on static (e.g., ImageNet) and neuromorphic (e.g., CIFAR10-DVS) datasets demonstrate that our TaWQ maintains high energy efficiency (4.12M, 0.63mJ) while incurring a negligible quantization loss of only 0.22% on ImageNet.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm
Test-Time adaptation (TTA) has proven effective in mitigating performance drops under single-domain distribution shifts by updating model parameters during inference. However, real-world deployments often involve mixed distribution shifts, where test samples are affected by diverse and potentially conflicting domain factors, posing significant challenges even for SOTA TTA methods. A key limitation in existing approaches is their reliance on a unified adaptation path, which fails to account for the fact that optimal gradient directions can vary significantly across different domains. Moreover, current benchmarks focus only on synthetic or homogeneous shifts, failing to capture the complexity of real-world heterogeneous mixed distribution shifts. To address this, we propose MoETTA, a novel entropy-based TTA framework that integrates the Mixture-of-Experts (MoE) architecture. Rather than enforcing a single parameter update rule for all test samples, MoETTA introduces a set of structurally decoupled experts, enabling adaptation along diverse gradient directions. This design allows the model to better accommodate heterogeneous shifts through flexible and disentangled parameter updates. To simulate realistic deployment conditions, we introduce two new benchmarks: potpourri and potpourri+. While classical settings focus solely on synthetic corruptions, potpourri encompasses a broader range of domain shifts–including natural, artistic, and adversarial distortions–capturing more realistic deployment challenges. Additionally, potpourri+ further includes source-domain samples to evaluate robustness against catastrophic forgetting. Extensive experiments across three mixed distribution shifts settings show that MoETTA consistently outperforms strong baselines, establishing SOTA performance and highlighting the benefit of modeling multiple adaptation directions via expert-level diversity.
Read the full abstract
Computer Vision
From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing
Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill-posed and can erase structure and illumination details. To address this, we use event cameras for dehazing for the first time. Event cameras offer much higher HDR ($120 dBvs.60 dB$) and microsecond latency, therefore they suit hazy scenes. In practice, transferring HDR cues from events to frames is hard because real paired data are scarce. To tackle this, we propose an event-guided diffusion model that utilizes the strong generative priors of diffusion models to reconstruct clear images from hazy inputs by effectively transferring HDR information from events. Specifically, we design an event-guided module that maps sparse HDR event features, e.g., edges, corners, into the diffusion latent space. This clear conditioning provides precise structural guidance during generation, improves visual realism, and reduces semantic drift. For real-world evaluation, we collect a drone dataset in heavy haze (AQI = 341) with synchronized RGB and event sensors. Experiments on two benchmarks and our dataset achieve state-of-the-art results.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
A Deep Learning Framework for Thyroid Nodule Segmentation and Malignancy Classification from Ultrasound Images
Ultrasound-based risk stratification of thyroid nodules is a critical clinical task, but it suffers from high inter-observer variability. While many deep learning (DL) models function as "black boxes," we propose a fully automated, two-stage framework for interpretable malignancy prediction. Our method achieves interpretability by forcing the model to focus only on clinically relevant regions. First, a TransUNet model automatically segments the thyroid nodule. The resulting mask is then used to create a region of interest around the nodule, and this localised image is fed directly into a ResNet-18 classifier. We evaluated our framework using 5-fold cross-validation on a clinical dataset of 349 images, where it achieved a high F1-score of 0.852 for predicting malignancy. To validate its performance, we compared it against a strong baseline using a Random Forest classifier with hand-crafted morphological features, which achieved an F1-score of 0.829. The superior performance of our DL framework suggests that the implicit visual features learned from the localised nodule are more predictive than explicit shape features alone. This is the first fully automated end-to-end pipeline for both detecting thyroid nodules on ultrasound images and predicting their malignancy.