寻找丢失的在线测试时间适应性:调查

IF 11.6 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Zixin Wang, Yadan Luo, Liang Zheng, Zhuoxiao Chen, Sen Wang, Zi Huang
{"title":"寻找丢失的在线测试时间适应性:调查","authors":"Zixin Wang, Yadan Luo, Liang Zheng, Zhuoxiao Chen, Sen Wang, Zi Huang","doi":"10.1007/s11263-024-02213-5","DOIUrl":null,"url":null,"abstract":"<p>This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer. Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.</p>","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":null,"pages":null},"PeriodicalIF":11.6000,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"In Search of Lost Online Test-Time Adaptation: A Survey\",\"authors\":\"Zixin Wang, Yadan Luo, Liang Zheng, Zhuoxiao Chen, Sen Wang, Zi Huang\",\"doi\":\"10.1007/s11263-024-02213-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer. Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.</p>\",\"PeriodicalId\":13752,\"journal\":{\"name\":\"International Journal of Computer Vision\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":11.6000,\"publicationDate\":\"2024-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Computer Vision\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s11263-024-02213-5\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Vision","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11263-024-02213-5","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

本文介绍了在线测试时间适应(OTTA)的全面调查,重点是在批量数据到达后,如何有效地使机器学习模型适应分布不同的目标数据。尽管近来 OTTA 方法层出不穷,但由于模糊的设置、过时的骨架和不一致的超参数调整,以往研究的结论并不一致,这掩盖了核心挑战并阻碍了可重复性。为了提高清晰度并进行严格比较,我们将 OTTA 技术分为三个主要类别,并使用现代骨干网(Vision Transformer)对其进行基准测试。我们的基准涵盖了 CIFAR-10/100-C 和 ImageNet-C 等传统损坏数据集,以及以 CIFAR-10.1、OfficeHome 和 CIFAR-10-Warehouse 为代表的真实世界变化。CIFAR-10-Warehouse 数据集包括来自不同搜索引擎的各种变化以及通过扩散模型生成的合成数据。为了衡量在线场景中的效率,我们引入了新的评估指标,包括 GFLOPs、挂钟时间和 GPU 内存使用量,从而更清晰地反映了适应精度和计算开销之间的权衡。我们的研究结果与现有文献有所不同,揭示出:(1) 变压器对不同领域的变化表现出更强的适应能力;(2) 许多 OTTA 方法的功效依赖于较大的批量规模;(3) 优化的稳定性和对扰动的抵抗力在适应过程中至关重要,尤其是当批量规模为 1 时。我们的基准测试工具包和源代码可在 https://github.com/Jo-wang/OTTA_ViT_survey 上获取。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

In Search of Lost Online Test-Time Adaptation: A Survey

In Search of Lost Online Test-Time Adaptation: A Survey

This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer. Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
International Journal of Computer Vision
International Journal of Computer Vision 工程技术-计算机:人工智能
CiteScore
29.80
自引率
2.10%
发文量
163
审稿时长
6 months
期刊介绍: The International Journal of Computer Vision (IJCV) serves as a platform for sharing new research findings in the rapidly growing field of computer vision. It publishes 12 issues annually and presents high-quality, original contributions to the science and engineering of computer vision. The journal encompasses various types of articles to cater to different research outputs. Regular articles, which span up to 25 journal pages, focus on significant technical advancements that are of broad interest to the field. These articles showcase substantial progress in computer vision. Short articles, limited to 10 pages, offer a swift publication path for novel research outcomes. They provide a quicker means for sharing new findings with the computer vision community. Survey articles, comprising up to 30 pages, offer critical evaluations of the current state of the art in computer vision or offer tutorial presentations of relevant topics. These articles provide comprehensive and insightful overviews of specific subject areas. In addition to technical articles, the journal also includes book reviews, position papers, and editorials by prominent scientific figures. These contributions serve to complement the technical content and provide valuable perspectives. The journal encourages authors to include supplementary material online, such as images, video sequences, data sets, and software. This additional material enhances the understanding and reproducibility of the published research. Overall, the International Journal of Computer Vision is a comprehensive publication that caters to researchers in this rapidly growing field. It covers a range of article types, offers additional online resources, and facilitates the dissemination of impactful research.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信