Test-Time Adaptation with Principal Component Analysis
This addresses the issue of distribution shift for ML practitioners, but it is incremental as it builds on existing batch-norm adaptation approaches.
The paper tackles the problem of machine learning models failing under distribution shift by proposing a test-time adaptation method using principal component analysis (PCA) to filter layer outputs, achieving effectiveness with only 2000 parameters on CIFAR-10-C and CIFAR-100-C datasets.
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.