Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Zhilin, Hong, Xiaopeng, Ma, Zhiheng, Zhuang, Weijun, Ma, Yaohui, Dai, Yong, Wang, Yaowei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914876220243968
author Zhu, Zhilin
Hong, Xiaopeng
Ma, Zhiheng
Zhuang, Weijun
Ma, Yaohui
Dai, Yong
Wang, Yaowei
author_facet Zhu, Zhilin
Hong, Xiaopeng
Ma, Zhiheng
Zhuang, Weijun
Ma, Yaohui
Dai, Yong
Wang, Yaowei
contents Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting under continual domain shifts. To address these challenges, we reshape the online data buffering and organizing mechanism for CTTA. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream. Based on this, we propose a graph-based class relation preservation constraint to overcome catastrophic forgetting. Furthermore, a pseudo-target replay objective is used to mitigate error accumulation. Extensive experiments demonstrate the superiority of our method in both segmentation and classification CTTA tasks. Code is available at https://github.com/z1358/OBAO.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09367
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
Zhu, Zhilin
Hong, Xiaopeng
Ma, Zhiheng
Zhuang, Weijun
Ma, Yaohui
Dai, Yong
Wang, Yaowei
Computer Vision and Pattern Recognition
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting under continual domain shifts. To address these challenges, we reshape the online data buffering and organizing mechanism for CTTA. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream. Based on this, we propose a graph-based class relation preservation constraint to overcome catastrophic forgetting. Furthermore, a pseudo-target replay objective is used to mitigate error accumulation. Extensive experiments demonstrate the superiority of our method in both segmentation and classification CTTA tasks. Code is available at https://github.com/z1358/OBAO.
title Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.09367