Continual Test-time Domain Adaptation via Dynamic Sample Selection

TL;DR

This paper introduces a Dynamic Sample Selection method for continual test-time domain adaptation, improving model robustness across evolving target domains without source data access.

Contribution

It proposes a novel dynamic thresholding and joint positive-negative learning approach to handle noisy pseudo-labels in CTDA, outperforming existing methods.

Findings

Outperforms state-of-the-art in image domain CTDA

Effective in 3D point cloud domain

Reduces risk of using incorrect pseudo-labels

Abstract

The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA. DSS consists of dynamic thresholding, positive learning, and negative learning processes. Traditionally, models learn from unlabeled unknown environment data and equally rely on all samples' pseudo-labels to update their parameters through self-training. However, noisy predictions exist in these pseudo-labels, so all samples are not equally trustworthy. Therefore, in our method, a dynamic thresholding module is first designed to select suspected low-quality from high-quality samples. The selected low-quality samples are more likely to be wrongly predicted. Therefore, we apply joint positive and negative learning on both high- and low-quality samples to reduce the risk of using wrong information. We conduct extensive experiments that demonstrate the effectiveness of our proposed method for CTDA in the image domain, outperforming the state-of-the-art results. Furthermore, our approach is also evaluated in the 3D point cloud domain, showcasing its versatility and potential for broader applicability.