AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation

Yifan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41647-41676, 2023.

Abstract

Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various fields. Several literatures show that DG can be arbitrarily hard without exploiting target domain information. To address this issue, test-time adaptive (TTA) methods are proposed. Existing TTA methods require offline target data or extra sophisticated optimization procedures during the inference stage. In this work, we adopt Non-Parametric Classifier to perform the test-time Adaptation (AdaNPC). In particular, we construct a memory that contains the feature and label pairs from training domains. During inference, given a test instance, AdaNPC first recalls $k$ closed samples from the memory to vote for the prediction, and then the test feature and predicted label are added to the memory. In this way, the sample distribution in the memory can be gradually changed from the training distribution towards the test distribution with very little extra computation cost. We theoretically justify the rationality behind the proposed method. Besides, we test our model on extensive numerical experiments. AdaNPC significantly outperforms competitive baselines on various DG benchmarks. In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is $50$% higher than advanced TTA methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-zhang23am, title = {{A}da{NPC}: Exploring Non-Parametric Classifier for Test-Time Adaptation}, author = {Zhang, Yifan and Wang, Xue and Jin, Kexin and Yuan, Kun and Zhang, Zhang and Wang, Liang and Jin, Rong and Tan, Tieniu}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {41647--41676}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/zhang23am/zhang23am.pdf}, url = {https://proceedings.mlr.press/v202/zhang23am.html}, abstract = {Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various fields. Several literatures show that DG can be arbitrarily hard without exploiting target domain information. To address this issue, test-time adaptive (TTA) methods are proposed. Existing TTA methods require offline target data or extra sophisticated optimization procedures during the inference stage. In this work, we adopt Non-Parametric Classifier to perform the test-time Adaptation (AdaNPC). In particular, we construct a memory that contains the feature and label pairs from training domains. During inference, given a test instance, AdaNPC first recalls $k$ closed samples from the memory to vote for the prediction, and then the test feature and predicted label are added to the memory. In this way, the sample distribution in the memory can be gradually changed from the training distribution towards the test distribution with very little extra computation cost. We theoretically justify the rationality behind the proposed method. Besides, we test our model on extensive numerical experiments. AdaNPC significantly outperforms competitive baselines on various DG benchmarks. In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is $50$% higher than advanced TTA methods.} }
Endnote
%0 Conference Paper %T AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation %A Yifan Zhang %A Xue Wang %A Kexin Jin %A Kun Yuan %A Zhang Zhang %A Liang Wang %A Rong Jin %A Tieniu Tan %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-zhang23am %I PMLR %P 41647--41676 %U https://proceedings.mlr.press/v202/zhang23am.html %V 202 %X Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various fields. Several literatures show that DG can be arbitrarily hard without exploiting target domain information. To address this issue, test-time adaptive (TTA) methods are proposed. Existing TTA methods require offline target data or extra sophisticated optimization procedures during the inference stage. In this work, we adopt Non-Parametric Classifier to perform the test-time Adaptation (AdaNPC). In particular, we construct a memory that contains the feature and label pairs from training domains. During inference, given a test instance, AdaNPC first recalls $k$ closed samples from the memory to vote for the prediction, and then the test feature and predicted label are added to the memory. In this way, the sample distribution in the memory can be gradually changed from the training distribution towards the test distribution with very little extra computation cost. We theoretically justify the rationality behind the proposed method. Besides, we test our model on extensive numerical experiments. AdaNPC significantly outperforms competitive baselines on various DG benchmarks. In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is $50$% higher than advanced TTA methods.
APA
Zhang, Y., Wang, X., Jin, K., Yuan, K., Zhang, Z., Wang, L., Jin, R. & Tan, T.. (2023). AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:41647-41676 Available from https://proceedings.mlr.press/v202/zhang23am.html.

Related Material