NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

By Taesik Gong, Jongheon Jeong, Taewon Kim, Yewon Kim, Jinwoo Shin, Sung-Ju Lee. 2022

209 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Label-Efficient Incremental Learning: A Survey (2023, methodology): “TEst-time adaptation [Gong et al., 2022] extends COTTA to realistic scenes, where the subsequent test examples carry high temporal correlation, such as in the case of self-driving cars.”
A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “A pioneering approach, Tent [9], proposes minimizing the mean entropy over the test batch to update the affine parameters { γ, β } of BN layers in the pre-trained model, followed by various subsequent methods [314, 311].”