论文标题
重新审视现实的测试时间培训：通过锚定聚类的顺序推断和适应
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
论文作者
论文摘要
在目标域数据上部署模型需要进行分配转移，需要适应。测试时间培训（TTT）作为解决此适应的解决方案，在现实情况下，无法访问完整的源域数据，并且需要对目标域的即时推断。尽管在TTT上进行了许多努力，但在实验环境中仍存在混乱，从而导致了不公平的比较。在这项工作中，我们首先通过两个关键因素重新访问TTT假设并将TTT协议分类。在多个协议中，我们采用了现实的顺序测试时间训练（STTT）协议，在该协议下，我们进一步开发了一种测试时间锚定聚类（TTAC）方法来实现更强大的测试时间功能学习。 TTAC发现源域和目标域中的簇，并将目标簇与源簇匹配以改善概括。伪标签过滤和迭代更新是为了提高锚固聚类的有效性和效率。我们证明，在所有TTT协议下，TTAC始终优于六个TTT数据集上的最新方法。我们希望这项工作能够为TTT方法提供公平的基准测试，并应在各自的协议中比较未来的研究。可以在https://github.com/gorilla-lab-scut/ttac上获得演示代码。
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 six 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.
