NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
Preprint
Abstract
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model adaptation. Previous TTA schemes assume that the test samples are independent and identically distributed (i.i.d.), even though they are often temporally correlated (non-i.i.d.) in application scenarios, e.g., autonomous driving. We discover that most existing TTA methods fail dramatically under such scenarios. Motivated by this, we present a new test-time adaptation scheme that is robust against non-i.i.d. test data streams. Our novelty is mainly two-fold: (a) Instance-Aware Batch Normalization (IABN) that corrects normalization for out-of-distribution samples, and (b) Prediction-balanced Reservoir Sampling (PBRS) that simulates i.i.d. data stream from non-i.i.d. stream in a class-balanced manner. Our evaluation with various datasets, including real-world non-i.i.d. streams, demonstrates that the proposed robust TTA not only outperforms state-of-the-art TTA algorithms in the non-i.i.d. setting, but also achieves comparable performance to those algorithms under the i.i.d. assumption. Code is available at https://github.com/TaesikGong/NOTE.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Federated Learning on Non-IID Data Silos: An Experimental Study2022
- HARTH: A Human Activity Recognition Dataset for Machine LearningSensors, 2021
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- Recognizing Detailed Human Context in the Wild from Smartphones and SmartwatchesIEEE Pervasive Computing, 2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- A survey of mobile phone sensingIEEE Communications Magazine, 2010
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998