cs.CV · 2026-08-20 · No. 90
Computer Vision and Pattern Recognition, 2026-08-20.
21 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
21 entries-
01
Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
Longtian Wang, Zhengyu Zhao, Chenhao Lin, Le Yang, Shiwei Wang, Yuhan Zhi, Xiaofei Xie, Chao Shen
cs.CV · cs.AI
Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present. Existing detection methods either rely on trigger inversion or exploit architecture-specific assumptions, and critically, representative existing methods fail to generalize reliably to scene-level attacks, where a single trigger induces anomalous behavior across all objects...
-
02
SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection
Changshun Wu, Weicheng He, Xiaowei Huang, Saddek Bensalem
cs.CV · cs.LG
Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD) hallucinations. Existing approaches for detecting or mitigating such hallucinations typically either construct scoring functions directly over learned object detector representations or modify the object detector itself to suppress hallucination emergence. However, the latent priors implicitly...
-
03
ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models
Jihae Jeong, Junha Choi, Hwanjo Yu
cs.CV · cs.AI · cs.CL
Large vision-language models (LVLMs) often hallucinate, generating content that the input image does not support. Preventing such content during decoding calls for a candidate-specific measure of how strongly the image supports the token under consideration. The model's visual-token states offer a natural source of this evidence because projecting each state through the output head reveals which vocabulary items that position favors. These...
-
04
GS-VLA: Plug-and-Play Viewpoint Canonicalization for Frozen VLA Policies via Gaussian Splatting
Yechan Park, HyunJin Kim
cs.CV · cs.AI
This paper proposes a lightweight, plug-and-play framework that improves robustness to viewpoint shifts in Vision-Language-Action (VLA) policies without policy retraining. To our knowledge, this is the first approach to directly leverage 3D Gaussian-based novel-view synthesis for observation-space adaptation in VLA policies. Current VLA performance relies on the implicit assumption that training and deployment camera configurations are...
-
05
Counterfactual Contrastive Analysis
Yunlong He, Pietro Gori
cs.CV · cs.AI
Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the classifier's prediction. Existing VCE methods are inherently classifier-dependent and therefore susceptible to classifier biases and failure modes, such as sensitivity to shortcut features and calibration errors. In this paper, we propose a classifier-free approach for visual...
-
06
One-Stage Object Detectors in Autonomous Driving
Jonel Roman, Ryan Sirjue, Peter Nguyen, Daniel Krutky, Juan Jesus, Sudip Dhakal
cs.CV · cs.AI
Autonomous vehicles depend on fast and reliable perception systems to detect surrounding vehicles, pedestrians, cyclists, traffic signs, and other road objects in real time. This paper presents a comprehensive survey and analysis of one-stage object detectors for autonomous driving rather than an implementation of a new detection system. The survey reviews the evolution of major one-stage detectors, including YOLOv1, SSD, RetinaNet,...
-
07
GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery
Chaowei Wang, Yan Di, Jingjun Sun, Baozhe Liu, Jiaxu Tian, Yuheng Li, Guangqian Guo, Shan Gao
cs.CV · cs.AI
Visual grounding in Unmanned Aerial Vehicle (UAV) imagery aims to localize a target object in complex bird's-eye-view scenes according to a natural language description. However, the abundance of small, densely distributed, and visually similar objects creates high visual redundancy, while repetitive local configurations give rise to strong topological ambiguity. Existing approaches mainly focus on visual--language feature alignment or dense...
-
08
Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching
Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai, Marco Lents, Christian Ledig
cs.CV · cs.LG · eess.IV
Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classifiers. Existing remedies fall short: standard color jittering provides insufficient diversity, while deep generative style transfer algorithms hallucinate features, destroy clinically relevant structures, and waste massive compute resources. To address this, we revisit classical statistical...
-
09
Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets
Ting Xiang, Chenxi Deng, Jinhui Zhao, Bingting Jiang, Ke Zhang, Changjian Chen, Zhuo Tang
cs.CV · cs.AI
Small-scale image classification is often limited by the scarcity of training data. Generative data augmentation (GDA) based on pretrained generative models has emerged as an effective solution. However, existing methods rely on task-agnostic augmentation strategies that overlook downstream model needs. Although recent dynamic GDA methods incorporate model feedback to guide augmentation, they still struggle to reliably determine...
-
10
MIFR: A Modality-Invariant and Fair Representation Framework for Skin Disease Classification
Asonyu Senge Njih, Yvan Guifo Fodjo, Vianney Kengne Tchendji, Jerry Lacmou Zeutouo, Kerol Djoumessi
cs.CV · cs.LG
Skin diseases represent a major global public health burden, yet machine learning tools developed to assist in their diagnosis suffer from two critical limitations: reliance on only one modality for diagnosis and systematic performance disparities across skin tones. While existing approaches address each challenge separately, this work proposes a modality-invariant framework with fair representation (MIFR) for skin disease classification. The...
-
11
A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3
Sachin Dudda Nagaraju, Bendik Skarre Abrahamsen, Ashkan Moradi, Mattijs Elschot
cs.CV · cs.AI
Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSegmentator and MRSegmentator achieve strong performance, they require large annotated datasets for training. Medical foundation models offer a promising alternative through large-scale pretraining that reduces the annotation burden for new tasks, but zero-shot performance remains limited....
-
12
The Impact of CutMix on Reliability and Robustness in Semantic Segmentation
Steven Landgraf, Markus Ulrich
cs.CV · cs.AI · cs.LG
Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-critical applications such as autonomous driving. Despite the widespread use of CutMix - a simple yet powerful data augmentation strategy - its effect on the reliability and robustness in dense predictions tasks remains unexplored. Motivated by recent findings that semi-supervised segmentation...
-
13
A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation
Steven Landgraf, Joceline Hinz, Markus Ulrich
cs.CV · cs.AI · cs.LG
Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack of interpretability, tendency to be overconfident, and sensitivity to real-world domain shifts pose critical challenges for safety- and mission-critical applications. Uncertainty quantification (UQ) offers a principled way to address these issues, but its integration into...
-
14
Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts
Kartik Chincholikar, Kaushik Gopalan, Mihir Hasabnis
cs.CV · cs.AI
Digitizing the text from handwritten historical manuscripts is required to make them easily accessible, preservable, and to enable historical scholars to study them in new ways. Historical manuscripts, however, often exhibit complex heterogeneous layouts and non-standard appearance due to period-specific writing styles, page textures, camera noise, and other nuisance factors, making them difficult to perform OCR on. To tackle this challenge,...
-
15
Composed Historical Image Retrieval by Modeling Temporal Representations
Adrià Molina Rodríguez, Oriol Ramos Terrades, Josep Lladós Canet
cs.CV · cs.AI · cs.IR
While time evolves linearly, the geometry of neural embedding spaces is inherently multi-dimensional, often chaotic, and difficult to interpret. In principle, one could constrain an embedding space to a single temporal dimension; however, such a reduction would sacrifice performance on downstream tasks, as one-dimensional embeddings cannot retain sufficient expressive capacity. This paper asks whether it is possible to learn representations...
-
16
OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios
Zinuo Guo, Min Zhang, Bo Jiang
cs.CV · cs.AI
Multimodal large language models (MLLMs) are increasingly used as OCR systems in document and knowledge-processing pipelines, but their ability to faithfully read real handwriting remains underexplored. Existing OCR benchmarks focus largely on printed text or clean single-line inputs, leaving limited coverage of realistic handwritten OCR scenarios such as multilingual handwriting, writer errors, and structurally complex mathematical...
-
17
MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment
Yuan li, Youyuan Lin, Chenhui Chu, Shin'ya Nishida
cs.CV · cs.AI
Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (IQA) by improving consistency between quality ratings and their underlying reasoning. However, most approaches supervise reasoning through human-provided ratings and rarely examine whether it faithfully reflects image quality. Rating accuracy alone does not ensure faithful reasoning; a shared reward also obscures supervision sources and may...
-
18
Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection
Shashank Kotyan, Makoto Shing, Yuki Imajuku, Rujikorn Charakorn, Tarin Clanuwat
cs.CV · cs.AI
Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a...
-
19
OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation
Soumili Ghosh, Debapriya Roy, Aryan Das, Bikash Santra
cs.CV · cs.AI
Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while maintaining low computational requirements remains a significant challenge. In glaucoma detection, low-computation methods are crucial for enabling rapid, large-scale screening and facilitating deployment in resource-limited clinical environments. While deep...
-
20
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
Pardis Taghavi, Reza Langari, Gaurav Pandey
cs.CV · cs.AI · cs.LG
Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator. Queries sharing a block route may have poorly overlapping supports, while retained attention mass alone does not determine the post-softmax error from skipped interactions. We show that partition geometry affects both pooled support and the predictability of the remaining...
-
21
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs
Muhammad Haseeb Aslam, Alessandro Koerich, Marco Pedersoli, Ali Etemad, Eric Granger
cs.CV · cs.AI
Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild. ER is inherently multimodal, requiring a joint understanding of facial expressions, vocalizations, language, biosignals, and gestures. However, real-world deployment remains challenging: modalities may be missing or noisy at test time. Partial observations can be viewed as a distribution shift...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.