Removing tokens whose embeddings diverge most from a source or CLS-token prototype, selected by output entropy, improves 3D point cloud classification under distribution shift without backpropagation.
SMART–PC: Skeletal model adaptation for ro- bust test–time training in point clouds.Proceedings of the 42 nd International Conference on Machine Learning (ICML 2025), 2025a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging
Removing tokens whose embeddings diverge most from a source or CLS-token prototype, selected by output entropy, improves 3D point cloud classification under distribution shift without backpropagation.