Probabilistic Contrastive Test-Time Adaptation

Test-time adaptation (TTA) enhances generalization against out-of-distribution data during inference. Recent advances in TTA leverage some techniques such as contrastive learning and entropy minimization to improve the discriminability and robustness of models in target domains. However, existing me...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
Main Authors: You, Linjing, Lu, Jiabao, Huang, Xiayuan
Format: Conference Proceeding
Language:English
Published: IEEE 06.04.2025
Subjects:
Adaptation models
Contrastive learning
Distribution Shifts
Entropy
Heavily-tailed distribution
Label Shifts
Minimization
Probabilistic Contrastive Learning
Probabilistic logic
Robustness
Signal processing
Signal processing algorithms
Speech processing
Test-Time Adaptation
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Test-time adaptation (TTA) enhances generalization against out-of-distribution data during inference. Recent advances in TTA leverage some techniques such as contrastive learning and entropy minimization to improve the discriminability and robustness of models in target domains. However, existing methods often overlook simultaneous distribution shifts of sample and label, such as long-tail distributions, and contrastive learning approaches may require substantial storage for sample pairs. In this paper, we propose a novel Probabilistic Contrastive Test-time Adaptation (PCTA) method based on Expectation Maximization (EM), which is used to estimate the von Mises Fisher (vMF) distribution of test samples to capture both sample distribution and class proportions. The estimated distributions are used for probabilistic contrastive learning to adapt feature representations and optimize classification through class-weighted entropy minimization. Experimental results show that PCTA significantly enhances the performance across various distribution shifts and outperforms state-of-the-art methods in different scenarios involving both sample and label shifts. Code is available at https://github.com/youlj109/PCTA.
ISSN:2379-190X
DOI:10.1109/ICASSP49660.2025.10890260