paper-with-me

홈 › Papers

Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics

2024-07-08 · Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay

Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable navigation even in challenging environments such as adverse weather conditions (e.g., fog, rain), poor lighting conditions (e.g., over/under exposure), or sensor degradation (e.g., blurring, noise), and can guarantee high performance in safety-critical functions. Current solutions proposed to improve model robustness usually rely on generic data augmentation techniques or employ costly test-time adaptation methods. In addition, most approaches focus on addressing a single vision task (typically, image recognition) utilising synthetic data. In this paper, we introduce Per-corruption Adaptation of Normalization statistics (PAN) to enhance the model robustness of vision systems. Our approach entails three key components: (i) a corruption type identification module, (ii) dynamic adjustment of normalization layer statistics based on identified corruption type, and (iii) real-time update of these statistics according to input data. PAN can integrate seamlessly with any convolutional model for enhanced accuracy in several robot vision tasks. In our experiments, PAN obtains robust performance improvement on challenging real-world corrupted image datasets (e.g., OpenLoris, ExDark, ACDC), where most of the current solutions tend to fail. Moreover, PAN outperforms the baseline models by 20-30% on synthetic benchmarks in object recognition tasks.

📄 PDF Abstract BibTeX arXiv:2407.06450

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationObject RecognitionTest-time Adaptation

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

2023-06-03 · NeurIPS 2023 11

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to enhance the performance of pre-trained vision-language models in specific domains. The robustness of these adaptation methods against…

Benchmarking

Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions

2026-04-26 · Francesco Olivato, Cigdem Beyan, Vittorio Murino arxiv

In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by natural image corruptions that go beyond additive noise, including blur…

Unsupervised Domain AdaptationTest-time Adaptation

Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions

2023-05-09 · Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov

Robustness is a fundamental property of machine learning classifiers required to achieve safety and reliability. In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stabilit…

Adversarial RobustnessData AugmentationImage Classification

Towards Corruption-Agnostic Robust Domain Adaptation

2021-04-21 · Yifan Xu, Kekai Sheng, WeiMing Dong, Baoyuan Wu 외

Big progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domain are i.i.d. with training target domains. However, due to unpredictable cor…

Domain Adaptation

Improving robustness against common corruptions by covariate shift adaptation

2020-06-30 · NeurIPS 2020 12 · Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann 외

Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks…

Domain GeneralizationImage ClassificationOut-of-Distribution GeneralizationUnsupervised Domain Adaptation