Copertina

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Agnihotri, Shashank, Schader, David, Sharei, Nico, Kaçar, Mehmet Ege, Keuper, Margret
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
di: Agnihotri, Shashank, et al.
Pubblicazione: (2025)

DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
di: Agnihotri, Shashank, et al.
Pubblicazione: (2025)

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
di: Agnihotri, Shashank, et al.
Pubblicazione: (2023)

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context
di: Agnihotri, Shashank, et al.
Pubblicazione: (2023)

Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging
di: Poggi, Nicolas, et al.
Pubblicazione: (2025)

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
di: Oei, Victor, et al.
Pubblicazione: (2025)

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
di: Kleinmann, Marcel, et al.
Pubblicazione: (2025)

Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
di: Walter, Jan Philip, et al.
Pubblicazione: (2026)

How Do Training Methods Influence the Utilization of Vision Models?
di: Gavrikov, Paul, et al.
Pubblicazione: (2024)

AIM: Amending Inherent Interpretability via Self-Supervised Masking
di: Alshami, Eyad, et al.
Pubblicazione: (2025)

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
di: Agnihotri, Shashank, et al.
Pubblicazione: (2024)

Vision At Night: Exploring Biologically Inspired Preprocessing For Improved Robustness Via Color And Contrast Transformations
di: Stracke, Lorena, et al.
Pubblicazione: (2025)

RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images
di: Fatima, Mishal, et al.
Pubblicazione: (2026)

GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
di: Basu, Abhipsa, et al.
Pubblicazione: (2026)

Deepfakes: we need to re-think the concept of "real" images
di: Keuper, Janis, et al.
Pubblicazione: (2025)

$γ$-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
di: Fatima, Mishal, et al.
Pubblicazione: (2025)

Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption
di: Erol, Mehmet Kaan
Pubblicazione: (2026)

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
di: Grabinski, Julia, et al.
Pubblicazione: (2023)

Is Your HD Map Constructor Reliable under Sensor Corruptions?
di: Hao, Xiaoshuai, et al.
Pubblicazione: (2024)

Stylized Synthetic Augmentation further improves Corruption Robustness
di: Siedel, Georg, et al.
Pubblicazione: (2025)

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
di: Gou, Yunhao, et al.
Pubblicazione: (2025)

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
di: Lorenz, Peter, et al.
Pubblicazione: (2022)

Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data
di: Wang, An, et al.
Pubblicazione: (2024)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
di: Xu, Jiawen, et al.
Pubblicazione: (2024)

Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
di: Müller, Patrick, et al.
Pubblicazione: (2025)

Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
di: Fatima, Mishal, et al.
Pubblicazione: (2025)

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
di: Lorenz, Peter, et al.
Pubblicazione: (2021)

Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions
di: Siedel, Georg, et al.
Pubblicazione: (2023)

Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
di: Wang, Jie, et al.
Pubblicazione: (2024)

A High-Quality Robust Diffusion Framework for Corrupted Dataset
di: Dao, Quan, et al.
Pubblicazione: (2023)

DRIVE-C: A Controlled Corruption Dataset for Autonomous Driving
di: Aher, Shiva
Pubblicazione: (2026)

Analysing the Robustness of Vision-Language-Models to Common Corruptions
di: Usama, Muhammad, et al.
Pubblicazione: (2025)

Benchmarking the Robustness of UAV Tracking Against Common Corruptions
di: Liu, Xiaoqiong, et al.
Pubblicazione: (2024)

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
di: Grabinski, Julia, et al.
Pubblicazione: (2023)

I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames
di: Prasse, Katharina, et al.
Pubblicazione: (2024)

CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions
di: Chen, Gong, et al.
Pubblicazione: (2026)

A Survey on the Robustness of Computer Vision Models against Common Corruptions
di: Wang, Shunxin, et al.
Pubblicazione: (2023)

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
di: Oh, Yeongtak, et al.
Pubblicazione: (2024)

SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
di: Essl, Markus, et al.
Pubblicazione: (2026)

Detecting AutoAttack Perturbations in the Frequency Domain
di: Lorenz, Peter, et al.
Pubblicazione: (2021)