AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation

Zhixiang Chi, Yanan Wu, Li Gu, Huan Liu, Ziqiang Wang, Yang Zhang, Yang Wang, Konstantinos Plataniotis

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 7 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 FSA to MaskCLIPMaskCLIP (ViT-L/14) · 8 segmentation benchmarksmIoU: 13.9 -> 32.6Improved
add FSA to SCLIPSCLIP (ViT-L/14) · 8 segmentation benchmarksmIoU: 29.0 -> 35.0Improved
add FSA to ClearCLIPClearCLIP (ViT-B/16) · 8 segmentation benchmarksmIoU: 38.1 -> 38.8Improved
add FSA to ProxyCLIPProxyCLIP (ViT-H/14) · 8 segmentation benchmarksmIoU: 44.4 -> 45.8Improved
add FSA to ProxyCLIP with MAEProxyCLIP (ViT-L/14) · 8 segmentation benchmarksmIoU: 35.8 -> 38.3Improved
add FSA to Q-K attentionCLIP ViT-H/14 · 8 segmentation benchmarksmIoU: 30.0 -> 34.6Improved
add confidence-based pruning instead of fixed ratio (ablation)FSA on ProxyCLIP · 8 benchmarksmIoU: 37.8 -> 39.4Improved
add adaptive exponential scaling (ablation)FSA on ProxyCLIP · 8 benchmarksmIoU: 39.4 -> 43.6Improved
add attention isolation (ablation)FSA on MaskCLIP · 8 benchmarksmIoU: 29.8 -> 32.6Improved
add attention isolation (ablation)FSA on ProxyCLIP · 8 benchmarksmIoU: 43.4 -> 43.6Improved
ensemble three dense outputs (ablation)FSA on MaskCLIP · 8 benchmarksmIoU: 32.1 -> 32.6Improved
use KL divergence instead of cosine similarity (ablation)FSA on ProxyCLIP · 8 benchmarksmIoU: 43.3 -> 43.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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