English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deploying models on target domain data subject to distribution shift requiresadaptation. Test-time training (TTT) emerges as a solution to this adaptationunder a realistic scenario where access to full source domain data is notavailable and instant inference on target domain is required. Despite manyefforts into TTT, there is a confusion over the experimental settings, thusleading to unfair comparisons. In this work, we first revisit TTT assumptionsand categorize TTT protocols by two key factors. Among the multiple protocols,we adopt a realistic sequential test-time training (sTTT) protocol, under whichwe further develop a test-time anchored clustering (TTAC) approach to enablestronger test-time feature learning. TTAC discovers clusters in both source andtarget domain and match the target clusters to the source ones to improvegeneralization. Pseudo label filtering and iterative updating are developed toimprove the effectiveness and efficiency of anchored clustering. We demonstratethat under all TTT protocols TTAC consistently outperforms the state-of-the-artmethods on six TTT datasets. We hope this work will provide a fair benchmarkingof TTT methods and future research should be compared within respectiveprotocols. A demo code is available athttps://github.com/Gorilla-Lab-SCUT/TTAC.

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