AI Paper Atlas

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

Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective

Jiahao Li, Yang Lu, Yachao Zhang, Yong Xie, Fangyong Wang, Yuan Xie, Yanyun Qu

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 4 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
mask distraction tokens with -inf (ablation)Attn_kk-proxy CLIP · 4-benchmark averagemIoU: 32.1 -> 1.4Hurt
clamp distraction token embeddings to tau (low-pass filtering) (ablation)Attn_kk-proxy CLIP · 4-benchmark averagemIoU: 32.1 -> 4.2Hurt
replace distraction token embeddings with 3x3 mean of neighbors (ablation)Attn_kk-proxy CLIP · 4-benchmark averagemIoU: 32.1 -> 34.2Improved
replace distraction token embeddings with 3x3 median of neighbors (ablation)Attn_kk-proxy CLIP · 4-benchmark averagemIoU: 32.1 -> 33.6Improved
3x3 mean filtering on 10 random tokens (ablation)layer-averaged Attn_kk CLIP · 4-benchmark averagemIoU: 32.9 -> 31.6Hurt
apply the same filtering on localized distraction tokens instead of random tokens (ablation)RF-CLIP · 4-benchmark averagemIoU: 31.6 -> 34.0Improved
add attention weight redistribution (ablation)RF-CLIP (III) · 4-benchmark averagemIoU: 34.0 -> 35.0Improved
add embedding weight redistribution (ablation)RF-CLIP (III) · 4-benchmark averagemIoU: 34.0 -> 35.7Improved
add defocus localization to direct freed attention to target regions (ablation)RF-CLIP (VI) · 4-benchmark averagemIoU: 36.6 -> 38.2Improved
send redistribution budget to defocused tokens instead of all non-distraction tokens (ablation)RF-CLIP · 4-benchmark averagemIoU: 36.6 -> 38.2Improved
send redistribution budget to [CLS] token instead of non-distraction tokens (ablation)RF-CLIP · 4-benchmark averagemIoU: 36.6 -> 34.2Hurt
enlarge embedding redistribution neighborhood from 3x3 to 7x7 (ablation)RF-CLIP · 4-benchmark averagemIoU: 38.2 -> 36.1Hurt

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