Papers › TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models...

TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning

11 Dec 2024arXiv:2412.08176archive 2025-07-28

Jingjing Xie, Yuxin Zhang, Jun Peng, Zhaohong Huang, Liujuan Cao

Despite the efficiency of prompt learning in transferring vision-language models (VLMs) to downstream tasks, existing methods mainly learn the prompts in a coarse-grained manner where the learned prompt vectors are shared across all categories. Consequently, the tailored prompts often fail to discern class-specific visual concepts, thereby hindering the transferred performance for classes that share similar or complex visual attributes. Recent advances mitigate this challenge by leveraging external knowledge from Large Language Models (LLMs) to furnish class descriptions, yet incurring notable inference costs. In this paper, we introduce TextRefiner, a plug-and-play method to refine the text prompts of existing methods by leveraging the internal knowledge of VLMs. Particularly, TextRefiner builds a novel local cache module to encapsulate fine-grained visual concepts derivedfrom local tokens within the image branch. By aggregating and aligning the cached visual descriptions with the original output of the text branch, TextRefiner can efficiently refine and enrich the learned prompts from existing methods without relying on any external expertise. For example, it improves the performance of CoOp from 71.66 % to 76.94 % on 11 benchmarks, surpassing CoCoOp which introduces instance-wise features for text prompts. Equipped with TextRefiner, PromptKD achieves state-of-the-art performance and is efficient in inference. Our code is relesed at https://github.com/xjjxmu/TextRefiner

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xjjxmu/textrefiner officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Prompt Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CoOp

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections