Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationObject RecognitionTest-time AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
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…
BenchmarkingDiscriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions
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 AdaptationInvestigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions
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 ClassificationTowards Corruption-Agnostic Robust Domain Adaptation
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 AdaptationImproving robustness against common corruptions by covariate shift adaptation
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