Image de couverture de livre

Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Huakun, Hu, Boyue Caroline, Czarnecki, Krzysztof, Marsso, Lina, Chechik, Marsha
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MFSeg: Efficient Multi-frame 3D Semantic Segmentation
par: Huang, Chengjie, et autres
Publié: (2025)

Diagnosis via Proofs of Unsatisfiability for First-Order Logic with Relational Objects
par: Feng, Nick, et autres
Publié: (2024)

Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
par: Azadani, Mozhgan Nasr, et autres
Publié: (2025)

VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking
par: Xu, Boyue, et autres
Publié: (2026)

Per-Query Visual Concept Learning
par: Malca, Ori, et autres
Publié: (2025)

HAWAII: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models
par: Wang, Yimu, et autres
Publié: (2025)

VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation
par: Huang, Chengjie, et autres
Publié: (2024)

SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling
par: Huang, Chengjie, et autres
Publié: (2024)

How Hard Is Snow? A Paired Domain Adaptation Dataset for Clear and Snowy Weather: CADC+
par: Tang, Mei Qi, et autres
Publié: (2025)

Benchmarking the Robustness of UAV Tracking Against Common Corruptions
par: Liu, Xiaoqiong, et autres
Publié: (2024)

Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation
par: Kappan, Marsha Mariya, et autres
Publié: (2024)

Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection
par: Arsenos, Anastasios, et autres
Publié: (2024)

SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction
par: Bhattacharyya, Prarthana, et autres
Publié: (2024)

OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection
par: Chow, Adrian, et autres
Publié: (2025)

LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts
par: Wang, Yimu, et autres
Publié: (2025)

Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds
par: Shaar, Eitan, et autres
Publié: (2025)

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
par: Gou, Yunhao, et autres
Publié: (2025)

Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs
par: Orjuela, Daniel Yezid Guarnizo, et autres
Publié: (2026)

ResLPR: A LiDAR Data Restoration Network and Benchmark for Robust Place Recognition Against Weather Corruptions
par: Kuang, Wenqing, et autres
Publié: (2025)

Concept-based Analysis of Neural Networks via Vision-Language Models
par: Mangal, Ravi, et autres
Publié: (2024)

Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption
par: Tesema, Keneni W., et autres
Publié: (2025)

Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Training
par: Tian, Zhiqiang, et autres
Publié: (2025)

Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
par: Zheng, Laura, et autres
Publié: (2024)

Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks
par: Shao, Zhenan, et autres
Publié: (2024)

Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency
par: Boyd, Aidan, et autres
Publié: (2024)

Analysing the Robustness of Vision-Language-Models to Common Corruptions
par: Usama, Muhammad, et autres
Publié: (2025)

Benchmarking Corruption Robustness of LVLMs: A Discriminative Benchmark and Robustness Alignment Metric
par: Sui, Xiangjie, et autres
Publié: (2025)

A High-Quality Robust Diffusion Framework for Corrupted Dataset
par: Dao, Quan, et autres
Publié: (2023)

SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
par: Essl, Markus, et autres
Publié: (2026)

RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network
par: Xu, Boyue, et autres
Publié: (2025)

RGB-D Video Object Segmentation via Enhanced Multi-store Feature Memory
par: Xu, Boyue, et autres
Publié: (2025)

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
par: Zeng, Runhao, et autres
Publié: (2024)

A Survey on the Robustness of Computer Vision Models against Common Corruptions
par: Wang, Shunxin, et autres
Publié: (2023)

Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises
par: Choi, Minkyu, et autres
Publié: (2022)

Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation
par: Wang, Yimu, et autres
Publié: (2025)

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
par: Agnihotri, Shashank, et autres
Publié: (2025)

FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images
par: Camuffo, Elena, et autres
Publié: (2024)

Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
par: Camuffo, Elena, et autres
Publié: (2024)

Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific Diagrams
par: Zhou, Minghao, et autres
Publié: (2025)

Assessing Image Quality Using a Simple Generative Representation
par: Raviv, Simon, et autres
Publié: (2024)