Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
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.
Code (1)
Tasks
BenchmarkingClusteringPseudo LabelPseudo Label FilteringSimilar Papers 제목 키워드 기반
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 requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain da…
BenchmarkingClusteringSequentially Auditing Differential Privacy
We propose a practical sequential test for auditing differential privacy guarantees of black-box mechanisms. The test processes streams of mechanisms' outputs providing anytime-valid inference while controlling Type I er…
ATTS: Asynchronous Test-Time Scaling via Conformal Prediction
Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency. Speculative decoding is a natural way to accelerate the scaling process; however, scaling along both the paral…
Ordinal ClassificationBooVAE: A Scalable Framework for Continual VAE Learning under Boosting Approach
Variational Auto Encoders (VAE) are capable of generating realistic images, sounds and video sequences. From practitioners point of view, we are usually interested in solving problems where tasks are learned sequentially…
Image GenerationNeRF Director: Revisiting View Selection in Neural Volume Rendering
Neural Rendering representations have significantly contributed to the field of 3D computer vision. Given their potential, considerable efforts have been invested to improve their performance. Nonetheless, the essential …
NeRFNeural Rendering