paper-with-me

홈 › Papers

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

2022-06-06 · Yongyi Su, Xun Xu, Kui Jia

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.

📄 PDF Abstract BibTeX arXiv:2206.02721

Code (1)

gorilla-lab-scut/ttac 공식 구현 pytorch

Tasks

BenchmarkingClusteringPseudo LabelPseudo Label Filtering

Similar Papers 제목 키워드 기반

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

2023-03-20 · Yongyi Su, Xun Xu, Tianrui Li, Kui Jia

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…

BenchmarkingClustering

Sequentially Auditing Differential Privacy

2025-09-08 · Tomás González, Mateo Dulce-Rubio, Aaditya Ramdas, Mónica Ribero arxiv

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

2025-09-18 · Jing Xiong, Qiujiang Chen, Fanghua Ye, Zhongwei Wan 외 arxiv

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 Classification

BooVAE: A Scalable Framework for Continual VAE Learning under Boosting Approach

2019-10-16 · pproximateinference AABI Symposium 2019 12 · Anna Kuzina, Evgenii Egorov, Evgeny Burnaev

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 Generation

NeRF Director: Revisiting View Selection in Neural Volume Rendering

2024-06-13 · CVPR 2024 1 · Wenhui Xiao, Rodrigo Santa Cruz, David Ahmedt-Aristizabal, Olivier Salvado 외

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