Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
Nov 28, 2022
Speakers
About
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.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 f…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection
Watch later
Abir De, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep Transformer Q-Networks for Partially Observable Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Inherently Explainable Reinforcement Learning in Natural Language
Watch later
Xiangyu Peng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On Scalable Testing of Samplers
Watch later
Yash Pote, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Online Reinforcement Learning for Mixed Policy Scopes
Watch later
Junzhe Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality
Watch later
Wei-Ning Hsu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%