Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2503.10685v3 Announce Type: replace Abstract: Unsupervised Domain Adaptation (UDA) enables strong generalization from a labeled source domain to an unlabeled target domain, often with limited d...
arXiv:2504.18190v2 Announce Type: replace Abstract: Unsupervised Domain Adaptation (UDA) can improve a perception model's generalization to an unlabeled target domain starting from a labeled source d...
arXiv:2507.08375v2 Announce Type: replace Abstract: Video restoration and enhancement are critical not only for improving visual quality, but also as essential pre-processing steps to boost the perfo...
The study investigates how the choice between processing page images or parsed text in an information extraction pipeline depends on the document’s layout, focusing on privacy‑sensitive, on‑premise scenarios with small models (≤8 B parameters). It evaluates accuracy and energy consumption across input representations, model families, and inference settings, finding that batching dramatically reduces energy use, FP8 quantization offers modest savings, and neural OCR is far more energy‑intensive than classical OCR. The optimal representation varies: vision‑language models excel on layout‑rich documents, while small text‑only models with a cheap parser perform best on near‑plain‑text contracts, achieving higher accuracy and lower energy than any vision‑language setup.
MedTokenBudget introduces a supervised token routing framework for Vision Transformers applied to dermoscopic image classification. Its Lesion-Aware Token Scoring (LATS) module combines attention entropy, feature norm, and local feature contrast to select the top‑K patches under a target budget, trained with curriculum learning, diversity regularization, attention distillation, and lesion‑mask supervision. On the ISIC 2019 dataset, mask‑supervised LATS outperforms Random and ToMe at headline budgets while retaining more lesion patches.
The paper investigates combining a domain‑specific self‑supervised task—voxel‑level brain age prediction—with a general task—image inpainting—to pretrain models for brain MRI segmentation. A multitask pretraining framework jointly optimizes both objectives, yielding representations that outperform single‑task pretraining and training from scratch on three segmentation benchmarks (multiple sclerosis lesions, ischemic stroke lesions, and cortical structures). The study demonstrates that integrating domain‑specific and general self‑supervised tasks benefits the development of generalizable neuroimaging foundation models.
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.
The paper introduces SemISAC, a unified framework that integrates semantic communication and semantic sensing into a single dual‑function waveform. It employs a joint semantic encoder to extract task‑specific information for both communication and sensing, and uses an adaptive pilot configuration to balance channel estimation and sensing needs. In vehicular scenarios, SemISAC achieves segmentation accuracy comparable to dedicated semantic communication systems while outperforming conventional and semantic baselines in target recognition and range estimation.
UltraG-Bench is a large‑scale, multi‑task benchmark designed to evaluate pixel‑level evidence grounding in ultrasound images. It comprises 40 public segmentation datasets covering 13 anatomical categories and includes three progressive tasks—instruction‑guided segmentation, evidence‑grounded VQA, and evidence‑grounded report generation—with a total of 736,726 annotations. Evaluation of 14 state‑of‑the‑art models shows a significant gap between semantic understanding and fine‑grained pixel‑level localization, and the authors propose UltraG‑Agent, which combines a vision‑language model with the ultrasound‑specific segmentation model UltraSAM to improve both semantic prediction and visual grounding.
DepthEvidence is a 4B multimodal language model that integrates dense metric depth predictions into language generation. It employs a camera‑conditioned decoder to produce full‑resolution depth maps and a dense‑to‑language interface that converts these predictions into object‑aligned geometry tokens. The model is trained with geometric supervision and instruction tuning, and it sets new state‑of‑the‑art results on a Depth‑VQA benchmark and on instance‑level metric depth estimation across nine datasets.
The paper investigates how to choose the best quantized model from a family of compressed versions when target labels are scarce or unavailable. It finds that a simple rule based on minimum teacher distortion consistently selects the same eight‑bit, per‑channel, unclipped configuration, though this does not minimize empirical target cross‑entropy. The study also shows that confidence‑based estimators perform poorly in overconfident regimes, while output‑distribution estimators can outperform the teacher in some architectures, and that combining distortion with a supervised term can improve selection. Across 134 candidate families, teacher‑anchored selection reduces mean regret with very few labels, though the benefit diminishes after about 25 labels.
ReG-SAM is a SAM-based framework designed for 2D vessel segmentation in medical images. It introduces reference graph prompt embeddings (GPEs) and vascular prototype embeddings (VPEs) to capture global spatial and fine-grained modality-specific vessel features, respectively. By building a modality-wise vascular database and learning these embeddings from reference masks, ReG-SAM consistently outperforms existing baselines across 19 datasets, especially on thin vessels.
The paper "Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers" reports that vision‑language models (VLMs) struggle to read images containing two overlapping text layers—one with sharp contour lines and one with soft shading. Using the DecoyBench dataset of 300 such images, the authors evaluated six closed‑source VLMs under naive and guided prompting at high and low resolutions. While humans could read both layers accurately, the models reliably read only the contour layer at high resolution and failed to extract the shading layer; at low resolution, neither the models nor humans could read the contour layer, but the shading layer remained readable. "whyItMatters":"The study highlights a consistent limitation of current VLMs in handling typographic structures with multiple spatial frequency layers, underscoring their vulnerability to typographic attacks and the need for more robust text‑recognition capabilities."
arXiv:2603.02843v2 Announce Type: replace Abstract: Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during t...
The paper introduces a new HDR video reconstruction framework that uses a double-stream registration approach combined with pyramid fusion. It processes three consecutive frames by computing optical flow relative to the central frame and applying a midpoint displacement strategy to address severe overexposure. The resulting radiance and low‑dynamic‑range images are merged in a pyramid fusion stage to produce the final HDR output, and experiments show the method outperforms existing state‑of‑the‑art techniques.
The paper presents a multi‑stage framework for recognizing Kuzushiji characters in Japanese historical documents. It combines character detection, cropping, classification, reading‑order reconstruction via adaptive column clustering, and large‑language‑model‑based post‑OCR correction. The authors also augment data synthetically, correct dataset annotations, and introduce new test sets, achieving significant character error rate reductions on real, synthetic, and out‑of‑domain data.
ManiVid introduces a unified forensic analysis framework for manipulated videos, combining forgery detection, artifact grounding, and anomaly explanation. The authors release ManiVid-38K, a large dataset of 19K real‑fake video pairs with authenticity labels, forgery masks, and explanations, and a benchmark ManiVidBench with 1K balanced pairs. ManiVidLens, the proposed model, outperforms existing methods in artifact grounding and anomaly explanation while matching state‑of‑the‑art detection accuracy.
The paper introduces PICO, an end-to-end trainable model for 6DoF surgical tool pose estimation that uses multi-task learning to predict segmentation, depth, and pose parameters. It incorporates two geometry-aware proxy tasks—a projection loss and a point-to-point loss—to enforce consistency in 2D and 3D spaces, improving accuracy and robustness. Evaluated on the SurgRIPE dataset, PICO achieves strong performance, ranking second in rotation accuracy and maintaining competitive translation results, especially under occlusion.
TRACKGRAPH is an online open‑vocabulary 3D mapping system that tracks 2D masks in the image stream before fusing them into a class‑agnostic 3D segment layer within a hierarchical scene graph. It uses FastSAM and CLIP for sparse keyframes, DINOv3 for dense mask propagation, and compact multi‑view CLIP embeddings for open‑vocabulary retrieval. The method outperforms state‑of‑the‑art mapping techniques on Replica, ScanNet++, and HM3D, achieving higher synonym frequency, faster processing, and lower GPU memory usage, and has been deployed on quadruped robots and drones at real‑time rates.
The paper investigates how stable band‑selection methods are and how that stability relates to semantic segmentation performance on the Hyperspectral City V2 dataset. Six band‑selection techniques were tested on ten different class‑balanced ROI sets, producing 60 top‑25 band subsets. Results show that Sim‑LP has the highest intra‑method stability, and together with JMIM+CSNR it also delivers the best segmentation results, achieving up to 2.01 mIoU improvement and 18–22× faster CPU inference for a 9‑band subset, though stability does not consistently predict segmentation quality.