Test-Time Adaptation with Principal Component Analysis

Abstract

Machine Learning models are prone to fail when test data are different from training data, a situation often encountered in real applications known as distribution shift. While still valid, the training-time knowledge becomes less effective, requiring a test-time adaptation to maintain high performance. Following approaches that assume batch-norm layer and use their statistics for adaptation, we propose a Test-Time Adaptation with Principal Component Analysis (TTAwPCA), which presumes a fitted PCA and adapts at test time a spectral filter based on the singular values of the PCA for robustness to corruptions. TTAwPCA combines three components: the output of a given layer is decomposed using a Principal Component Analysis (PCA), filtered by a penalization of its singular values, and reconstructed with the PCA inverse transform. This generic enhancement adds fewer parameters than current methods. Experiments on CIFAR-10-C and CIFAR- 100-C demonstrate the effectiveness and limits of our method using a unique filter of 2000 parameters.

arXiv comment7 pages, 2 figures, 2 tables, accepted at Workshop on Trustworthy Artificial Intelligence in conjunction with ECML/PKDD 22

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Spectral Normalization for Generative Adversarial Networks
• Unsupervised Domain Adaptation by Backpropagation
• Unsupervised Domain Adaptation through Self-Supervision
• Improving robustness against common corruptions by covariate shift adaptation
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation