DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ye, Chuyang, Wei, Dongyan, Liu, Zhendong, Pang, Yuanyi, Lin, Yixi, Jiang, Qinting, Jiang, Jingyan, He, Dongbiao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917167722659840
author Ye, Chuyang
Wei, Dongyan
Liu, Zhendong
Pang, Yuanyi
Lin, Yixi
Jiang, Qinting
Jiang, Jingyan
He, Dongbiao
author_facet Ye, Chuyang
Wei, Dongyan
Liu, Zhendong
Pang, Yuanyi
Lin, Yixi
Jiang, Qinting
Jiang, Jingyan
He, Dongbiao
contents Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given time. They fail to handle the dynamic nature of real-world data, where single-domain and multiple-domain distributions change over time. We identify that performance drops in multiple-domain scenarios are caused by batch normalization errors and gradient conflicts, which hinder adaptation. To solve these challenges, we propose Domain Diversity Adaptive Test-Time Adaptation (DATTA), the first approach to handle TTA under dynamic domain shift data streams. It is guided by a novel domain-diversity score. DATTA has three key components: a domain-diversity discriminator to recognize single- and multiple-domain patterns, domain-diversity adaptive batch normalization to combine source and test-time statistics, and domain-diversity adaptive fine-tuning to resolve gradient conflicts. Extensive experiments show that DATTA significantly outperforms state-of-the-art methods by up to 13%. Code is available at https://github.com/DYW77/DATTA.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08056
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams
Ye, Chuyang
Wei, Dongyan
Liu, Zhendong
Pang, Yuanyi
Lin, Yixi
Jiang, Qinting
Jiang, Jingyan
He, Dongbiao
Machine Learning
Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given time. They fail to handle the dynamic nature of real-world data, where single-domain and multiple-domain distributions change over time. We identify that performance drops in multiple-domain scenarios are caused by batch normalization errors and gradient conflicts, which hinder adaptation. To solve these challenges, we propose Domain Diversity Adaptive Test-Time Adaptation (DATTA), the first approach to handle TTA under dynamic domain shift data streams. It is guided by a novel domain-diversity score. DATTA has three key components: a domain-diversity discriminator to recognize single- and multiple-domain patterns, domain-diversity adaptive batch normalization to combine source and test-time statistics, and domain-diversity adaptive fine-tuning to resolve gradient conflicts. Extensive experiments show that DATTA significantly outperforms state-of-the-art methods by up to 13%. Code is available at https://github.com/DYW77/DATTA.
title DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams
topic Machine Learning
url https://arxiv.org/abs/2408.08056