Realistic Evaluation of Test-Time Adaptation Algorithms: Unsupervised Hyperparameter Selection

• URL: http://arxiv.org/abs/2407.14231v1
• Date: Fri, 19 Jul 2024 11:58:30 GMT
• Title: Realistic Evaluation of Test-Time Adaptation Algorithms: Unsupervised Hyperparameter Selection
• Authors: Sebastian Cygert, Damian Sójka, Tomasz Trzciński, Bartłomiej Twardowski,
• Abstract summary: Test-Time Adaptation (TTA) has emerged as a promising strategy for tackling the problem of machine learning model robustness under distribution shifts. We evaluate existing TTA methods using surrogate-based hp-selection strategies to obtain a more realistic evaluation of their performance.
• Score: 1.4530711901349282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-Time Adaptation (TTA) has recently emerged as a promising strategy for tackling the problem of machine learning model robustness under distribution shifts by adapting the model during inference without access to any labels. Because of task difficulty, hyperparameters strongly influence the effectiveness of adaptation. However, the literature has provided little exploration into optimal hyperparameter selection. In this work, we tackle this problem by evaluating existing TTA methods using surrogate-based hp-selection strategies (which do not assume access to the test labels) to obtain a more realistic evaluation of their performance. We show that some of the recent state-of-the-art methods exhibit inferior performance compared to the previous algorithms when using our more realistic evaluation setup. Further, we show that forgetting is still a problem in TTA as the only method that is robust to hp-selection resets the model to the initial state at every step. We analyze different types of unsupervised selection strategies, and while they work reasonably well in most scenarios, the only strategies that work consistently well use some kind of supervision (either by a limited number of annotated test samples or by using pretraining data). Our findings underscore the need for further research with more rigorous benchmarking by explicitly stating model selection strategies, to facilitate which we open-source our code.

Related papers

• SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation [55.87169702896249]
  Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. We propose a framework to evaluate DA methods and present a fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment. Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
  arXiv  Detail & Related papers  (2024-07-16T12:52:29Z)
• Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection [40.06196132637536]
  Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. We propose to approach HILTTA by synergizing active learning and model selection. We demonstrate on 5 TTA datasets that the proposed HILTTA approach is compatible with off-the-shelf TTA methods.
  arXiv  Detail & Related papers  (2024-05-29T09:13:30Z)
• Active Test-Time Adaptation: Theoretical Analyses and An Algorithm [51.84691955495693]
  Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. We propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.
  arXiv  Detail & Related papers  (2024-04-07T22:31:34Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)
• TeST: Test-time Self-Training under Distribution Shift [99.68465267994783]
  Test-Time Self-Training (TeST) is a technique that takes as input a model trained on some source data and a novel data distribution at test time. We find that models adapted using TeST significantly improve over baseline test-time adaptation algorithms.
  arXiv  Detail & Related papers  (2022-09-23T07:47:33Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Efficient Test-Time Model Adaptation without Forgetting [60.36499845014649]
  Test-time adaptation seeks to tackle potential distribution shifts between training and testing data. We propose an active sample selection criterion to identify reliable and non-redundant samples. We also introduce a Fisher regularizer to constrain important model parameters from drastic changes.
  arXiv  Detail & Related papers  (2022-04-06T06:39:40Z)
• Parameter-free Online Test-time Adaptation [19.279048049267388]
  We show how test-time adaptation methods fare for a number of pre-trained models on a variety of real-world scenarios. We propose a particularly "conservative" approach, which addresses the problem with a Laplacian Adjusted Maximum Estimation (LAME) Our approach exhibits a much higher average accuracy across scenarios than existing methods, while being notably faster and have a much lower memory footprint.
  arXiv  Detail & Related papers  (2022-01-15T00:29:16Z)
• Active Testing: Sample-Efficient Model Evaluation [39.200332879659456]
  We introduce active testing: a new framework for sample-efficient model evaluation. Active testing addresses this by carefully selecting the test points to label. We show how to remove that bias while reducing the variance of the estimator.
  arXiv  Detail & Related papers  (2021-03-09T10:20:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.