AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models

Xinyu Chen, Haotian Zhai, Can Zhang, Xiupeng Shi, Ruirui Li

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 5 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 vision-text prototype residual learning with align and contrast lossesMCP · Cross-domain 10 datasets average (ViT-B/16)top-1 accuracy (%): 71.98 -> 72.61Improved
add residual learning (MCP++ over MCP)MCP · ImageNet (ViT-B/16)top-1 accuracy (%): 72.37 -> 72.64Improved
add residual learning (MCP++ over MCP)MCP · Cross-domain 10 datasets average (ResNet-50)top-1 accuracy (%): 65.08 -> 65.49Improved
add negative cache to entropy and align caches (ablation)MCP++ · ImageNet (ViT-B/16)top-1 accuracy (%): 72.49 -> 72.64Improved
add align cache to entropy and negative caches (ablation)MCP++ · ImageNet (ViT-B/16)top-1 accuracy (%): 71.73 -> 72.64Improved
add entropy cache to align and negative caches (ablation)MCP++ · ImageNet (ViT-B/16)top-1 accuracy (%): 72.54 -> 72.64Improved
add any single cache over CLIP baseline (ablation)MCP++ · ImageNet (ViT-B/16)top-1 accuracy (%): 66.73 -> 71.51Improved
add alignment loss (ablation)MCP++ · Aircrafttop-1 accuracy (%): 29.74 -> 30.07Improved
add contrastive loss (ablation)MCP++ · Aircrafttop-1 accuracy (%): 29.74 -> 29.92Improved
add both align and contrast losses (ablation)MCP++ · Aircrafttop-1 accuracy (%): 29.74 -> 30.18Improved
use multi-retrieval strategy over single retrieval (ablation)MCP++ · ImageNettop-1 accuracy (%): +3.16%Improved
use multi-retrieval strategy over single retrieval (ablation)MCP++ · Cross-domain 10 datasetstop-1 accuracy (%): +4.24%Improved

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