Tackling Model Mismatch with Mixup Regulated Test-Time Training

Bochao Zhang, Rui Shao, Jingda Du, Pc Yuen, Wei Luo

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Test-time training (TTT) is an emerging approach for addressing the problem of domain shift. In its framework, a test-time training phase is inserted between the training phase and the test phase. During the test-time training phase, the representation layers are adapted using an auxiliary task. Then the updated model will be used in the test phase. Although the idea is very intuitive, TTT does not demonstrate competitive performance compared with some other domain adaption methods. In this paper, we present both theoretical and empirical analyses to explain the subpar performance of TTT. In particular, we point out that TTT causes a new kind of problem, which we term as Model Mismatch. To address this problem of Model Mismatch, we analyse a simple yet effective method inspired by the idea of mixup in robust training. Such effectiveness is shown in the experimental results.

Original languageEnglish
Title of host publication2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings
EditorsYannis Manolopoulos, Zhi-Hua Zhou
PublisherIEEE
Number of pages7
ISBN (Electronic)9798350345032
DOIs
Publication statusPublished - 9 Oct 2023
Event10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023 - Thessaloniki, Greece
Duration: 9 Oct 202312 Oct 2023

Publication series

Name2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings

Conference

Conference10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023
Country/TerritoryGreece
CityThessaloniki
Period9/10/2312/10/23

Scopus Subject Areas

  • Information Systems and Management
  • Statistics, Probability and Uncertainty
  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems

User-Defined Keywords

  • mixup
  • model mismatch
  • test-time training

Fingerprint

Dive into the research topics of 'Tackling Model Mismatch with Mixup Regulated Test-Time Training'. Together they form a unique fingerprint.

Cite this