Skip to main navigation Skip to search Skip to main content

Parameter-free Online Test-time Adaptation

  • École de technologie supérieure
  • FiveAI Ltd.

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

222 Citations (Scopus)

Abstract

Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, it is important to focus on adapting these models to a variety of down-stream scenarios. An interesting and practical paradigm is online test-time adaptation, according to which training data is inaccessible, no labelled data from the test distribution is available, and adaptation can only happen at test time and on a handful of samples. In this paper, we investigate how test-time adaptation methods fare for a number of pre-trained models on a variety of real-world scenarios, significantly extending the way they have been originally evaluated. We show that they perform well only in narrowly-defined experimental setups and sometimes fail catastrophically when their hyperparameters are not selected for the same scenario in which they are being tested. Motivated by the inherent uncertainty around the conditions that will ultimately be encountered at test time, we propose a particularly 'conservative' approach, which addresses the problem with a Laplacian Adjusted Maximum-likelihood Estimation (LAME) objective. By adapting the model's output (not its parameters), and solving our objective with an efficient concave-convex procedure, our approach exhibits a much higher average accuracy across scenarios than existing methods, while being notably faster and have a much lower memory footprint. The code is available at https://github.com/fiveai/LAME.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
PublisherIEEE Computer Society
Pages8334-8343
Number of pages10
ISBN (Electronic)9781665469463
DOIs
Publication statusPublished - 2022
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States
Duration: 19 Jun 2022 → 24 Jun 2022

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2022-June
ISSN (Print)1063-6919

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Period19/06/22 → 24/06/22

!!!Keywords

  • Self-& semi-& meta- Efficient learning and inferences
  • Transfer/low-shot/long-tail learning

Fingerprint

Dive into the research topics of 'Parameter-free Online Test-time Adaptation'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this