Progressive Conservative Adaptation for Evolving Target Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Gangming, Chen, Chaoqi, He, Wenhao, Pan, Chengwei, Fang, Chaowei, Li, Jinpeng, Chen, Xilin, Yu, Yizhou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911772703719424
author Zhao, Gangming
Chen, Chaoqi
He, Wenhao
Pan, Chengwei
Fang, Chaowei
Li, Jinpeng
Chen, Xilin
Yu, Yizhou
author_facet Zhao, Gangming
Chen, Chaoqi
He, Wenhao
Pan, Chengwei
Fang, Chaowei
Li, Jinpeng
Chen, Xilin
Yu, Yizhou
contents Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge sequentially and have continuously evolving distributions. Restoring and adapting to such target data results in escalating computational and resource consumption over time. Hence, it is vital to devise algorithms to address the evolving domain adaptation (EDA) problem, \emph{i.e.,} adapting models to evolving target domains without access to historic target domains. To achieve this goal, we propose a simple yet effective approach, termed progressive conservative adaptation (PCAda). To manage new target data that diverges from previous distributions, we fine-tune the classifier head based on the progressively updated class prototypes. Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism. This mechanism restricts feature adaptation within essential dimensions, thus easing the inference related to historical knowledge. The proposed PCAda is implemented with a meta-learning framework, which achieves the fast adaptation of the classifier with the help of the progressively updated class prototypes in the inner loop and learns a generalized feature without severely interfering with the historic knowledge via the conservative sparse attention in the outer loop. Experiments on Rotated MNIST, Caltran, and Portraits datasets demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04573
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Progressive Conservative Adaptation for Evolving Target Domains
Zhao, Gangming
Chen, Chaoqi
He, Wenhao
Pan, Chengwei
Fang, Chaowei
Li, Jinpeng
Chen, Xilin
Yu, Yizhou
Computer Vision and Pattern Recognition
Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge sequentially and have continuously evolving distributions. Restoring and adapting to such target data results in escalating computational and resource consumption over time. Hence, it is vital to devise algorithms to address the evolving domain adaptation (EDA) problem, \emph{i.e.,} adapting models to evolving target domains without access to historic target domains. To achieve this goal, we propose a simple yet effective approach, termed progressive conservative adaptation (PCAda). To manage new target data that diverges from previous distributions, we fine-tune the classifier head based on the progressively updated class prototypes. Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism. This mechanism restricts feature adaptation within essential dimensions, thus easing the inference related to historical knowledge. The proposed PCAda is implemented with a meta-learning framework, which achieves the fast adaptation of the classifier with the help of the progressively updated class prototypes in the inner loop and learns a generalized feature without severely interfering with the historic knowledge via the conservative sparse attention in the outer loop. Experiments on Rotated MNIST, Caltran, and Portraits datasets demonstrate the effectiveness of our method.
title Progressive Conservative Adaptation for Evolving Target Domains
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.04573