AI Paper Atlas

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

Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models

Yiwen Liang, Hui Chen, Yizhe Xiong, Mengyao Lyu, Yuhan Cao, Zijia Lin, SHUAICHENG NIU, Sicheng Zhao, Jungong Han, Guiguang Ding

ECCV 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 0 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 region purification (RP) (ablation)PuRF baseline · COCO2017 (ViT-B/16)mAP (%): 60.71 -> 63.35Improved
add episodic purification (EP) of cache (ablation)PuRF baseline · COCO2017 (ViT-B/16)mAP (%): 60.71 -> 62.59Improved
add episodic purification to region purification (ablation)PuRF (RP only) · COCO2017 (ViT-B/16)mAP (%): 63.35 -> 64.56Improved
add temporal refreshing (TR) to RP+EP (ablation)PuRF (RP+EP) · COCO2017 (ViT-B/16)mAP (%): 64.56 -> 65.35Improved
add region purification to EP+TR (ablation)PuRF (EP+TR) · COCO2017 (ViT-B/16)mAP (%): 63.37 -> 65.35Improved
select regions by relative score instead of using all regions (ablation)PuRF · COCO2017 (ViT-B/16)mAP (%): 63.46 -> 65.35Improved
relative-score instead of absolute-score region selection (ablation)PuRF · COCO2017 (ViT-B/16)mAP (%): 65.02 -> 65.35Improved
use purified-region cache with entropy filtering instead of global-only cache (ablation)PuRF · COCO2017 (ViT-B/16)mAP (%): 62.21 -> 65.35Improved
max aggregation instead of average aggregation of cached regions (ablation)PuRF · COCO2017 (ViT-B/16)mAP (%): 64.92 -> 65.35Improved
min-entropy cache retrieval instead of global retrieval (ablation)PuRF · COCO2017 (ViT-B/16)mAP (%): 64.80 -> 65.35Improved
PuRF instead of ReTA on ViT-B/32ReTA · Average of five datasets (ViT-B/32)mAP (%): 65.83 -> 69.88Improved
PuRF instead of ReTA with MaPLe initReTA · Average of five datasets (ViT-B/16, MaPLe init)mAP (%): 70.88 -> 73.79Improved

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