Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

06/06/2022
by   Yongyi Su, et al.
1

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT) protocol, under which we further develop a test-time anchored clustering (TTAC) approach to enable stronger test-time feature learning. TTAC discovers clusters in both source and target domain and match the target clusters to the source ones to improve generalization. Pseudo label filtering and iterative updating are developed to improve the effectiveness and efficiency of anchored clustering. We demonstrate that under all TTT protocols TTAC consistently outperforms the state-of-the-art methods on five TTT datasets. We hope this work will provide a fair benchmarking of TTT methods and future research should be compared within respective protocols. A demo code is available at https://github.com/Gorilla-Lab-SCUT/TTAC.

READ FULL TEXT
research
03/20/2023

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training

Deploying models on target domain data subject to distribution shift req...
research
08/19/2023

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

Generalizing deep learning models to unknown target domain distribution ...
research
11/28/2022

Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations

Spurious correlations, or correlations that change across domains where ...
research
09/02/2023

pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation

Test Time Adaptation (TTA) is a pivotal concept in machine learning, ena...
research
07/24/2022

Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes

This paper proposes a novel test-time adaptation strategy that adjusts t...
research
07/07/2022

Back to the Source: Diffusion-Driven Test-Time Adaptation

Test-time adaptation harnesses test inputs to improve the accuracy of a ...
research
06/20/2022

Test-time image-to-image translation ensembling improves out-of-distribution generalization in histopathology

Histopathology whole slide images (WSIs) can reveal significant inter-ho...

Please sign up or login with your details

Forgot password? Click here to reset