AI Paper Atlas

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

S2C2Seg: Semantic-Spatial Consistency and Category Optimization for Open-Vocabulary Segmentation

Yuhao Qing, Yueying Wang, Chaoyang Chen, Weidong Zhang, Jie Wen, Xin Xu

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation

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 S2C2Seg to SCLIPSCLIP · 8-benchmark average (training-free OVSS)mIoU (avg): 38.2 -> 47.9Improved
add S2C2Seg to ProxyCLIPProxyCLIP · 8-benchmark average (training-free OVSS)mIoU (avg): 42.3 -> 49.1Improved
add S2C2Seg to CorrCLIPCorrCLIP · 8-benchmark average (training-free OVSS)mIoU (avg): 47.8 -> 51.2Improved
add CSS category subset selection (ablation)S2C2Seg (CSG only) · 8-benchmark average (CSS scoring ablation)mIoU (avg): 45.9 -> 49.1Improved
add CSG on top of CSS (ablation)S2C2Seg · VOC21mIoU: 70.4 -> 72.8Improved
add CSS on top of CSG (ablation)S2C2Seg · ADE20KmIoU: 21.7 -> 23.1Improved
add CSS (w/o CSG variant) on ADE20K (ablation)ProxyCLIP · ADE20KmIoU: 20.2 -> 20.4No clear effect
add spatial score to global score in CSS (ablation)S2C2Seg · 8-benchmark average (CSS scoring ablation)mIoU (avg): 45.9 -> 47.7Improved
use category-aware fusion instead of additive (ablation)S2C2Seg · Context59mIoU: 44.1 -> 48.7Improved
use multiplicative instead of additive fusion (ablation)S2C2Seg · Context59mIoU: 44.1 -> 42.8Hurt
vary lambda in 0.4-0.8, tau in 0.2-0.5, Kmax in 15-25 (ablation)S2C2Seg · VOC (ProxyCLIP)mIoU: 48.0-49.5No clear effect
use oracle ground-truth categories instead of CSS (ablation)S2C2Seg · 8-benchmark average (CSS scoring ablation)mIoU (avg): 49.1 -> 61.9Improved

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