AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token purging

Moslem Yazdanpanah, Ali Bahri, Mehrdad Noori, Sahar Dastani, Gustavo Adolfo Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add BatchNorm reset (ablation)PG-SP · ScanObjectNN-C meanTop-1 accuracy (%): 39.86 -> 49.13Improved
add BatchNorm reset (ablation)BFTT3D · ScanObjectNN-C meanTop-1 accuracy (%): 33.00 -> 45.76Improved
increase purge size up to about 100 tokens (ablation)PG · ScanObjectNN-C BackgroundTop-1 accuracy (%)Improved
excessive purging (purge size above about 100) (ablation)PG · ScanObjectNN-C BackgroundTop-1 accuracy (%)Hurt
select purge size by entropy over six candidates {0,2,4,8,16,32} (ablation)PG · ScanObjectNN-C DistortionTop-1 accuracy (%): 59 -> 62.48Improved
purge tokens (PG-SP) instead of BFTT3D backprop-free adaptationPG-SP · ScanObjectNN-C meanTop-1 accuracy (%): 33.00 -> 49.13Improved
apply PG-SP to real-world ScanObjectNN OBJ-BG variantPG-SP · ScanObjectNN OBJ-BGTop-1 accuracy (%): 74.18 -> 75.56Improved
apply PG-SP to real-world ScanObjectNN PB-T50-RS variantPG-SP · ScanObjectNN PB-T50-RSTop-1 accuracy (%): 56.77 -> 61.07Improved
apply PG-SP to Point-Mamba backbonePG-SP · ScanObjectNN-C mean (Mamba)Top-1 accuracy (%): 29.11 -> 41.42Improved
apply PG-SP to Point-Mamba backbonePG-SP · ShapeNet-C mean (Mamba)Top-1 accuracy (%): 51.92 -> 51.66No clear effect
use PG-SP instead of BFTT3D for computePG-SP · GPU time per batchms: 173.94 ms -> 14.07 msImproved
use PG-SP instead of BFTT3D for memoryPG-SP · GPU memoryMiB: 7400 MiB -> 1300 MiBImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy