What type of study is this?

This is a Experimental Study study.

September 30, 2025Open Access

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

Key Points

Token purging significantly improves adaptation accuracy in point cloud classification tasks.
PG-SP variant boosts accuracy by 10.3% compared to state-of-the-art methods, achieving robust performance.
Backpropagation-free technique operates at the token level, streamlining the adaptation process.
Rapid processing of point clouds makes this approach viable for real-time applications.

Abstract

Test-time adaptation (TTA) is crucial for mitigating performance degradation caused by distribution shifts in 3D point cloud classification. In this work, we introduce Token Purging (PG), a novel backpropagation-free approach that removes tokens highly affected by domain shifts before they reach attention layers. Unlike existing TTA methods, PG operates at the token level, ensuring robust adaptation without iterative updates. We propose two variants: PG-SP, which leverages source statistics, and PG-SF, a fully source-free version relying on CLS-token-driven adaptation. Extensive evaluations on ModelNet40-C, ShapeNet-C, and ScanObjectNN-C demonstrate that PG-SP achieves an average of +10. 3\% higher accuracy than state-of-the-art backpropagation-free methods, while PG-SF sets new benchmarks for source-free adaptation. Moreover, PG is 12. 4 times faster and 5. 5 times more memory efficient than our baseline, making it suitable for real-world deployment. Code is available at https: //github. com/MosyMosy/Purge-Gatehttps: //github. com/MosyMosy/Purge-Gate

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper