AI Paper Atlas

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

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li

ICLR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 2 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 reflection (two-stage render-and-refine instead of single-stage) (ablation)SocioReasoner · SocioSeg test (All dataset)gIoU: 48.5 -> 52.8Improved
add refinement stage after Stage-1 localization (ablation)SocioReasoner · SocioSeg test (All dataset)gIoU: 50.8 -> 52.8Improved
add refinement stage after Stage-1 localization (ablation)SocioReasoner · SocioSeg test (All dataset)F1: 57.5 -> 59.7Improved
use 2 points instead of 1 in refinement (ablation)SocioReasoner · SocioSeg test (All dataset)gIoU: 51.2 -> 52.8Improved
use 3 points instead of 2 in refinement (ablation)SocioReasoner · SocioSeg test (All dataset)gIoU: 52.8 -> 52.3 gIoU; cIoU 47.9 -> 48.9Mixed
train with RL instead of SFT (ablation)SocioReasoner · SocioSeg OOD (Map Style)gIoU: 42.0 -> 49.1Improved
train with RL instead of SFT (ablation)SocioReasoner · SocioSeg OOD (New Region)gIoU: 32.3 -> 43.4Improved
train with RL instead of SFT (ablation)SocioReasoner · SocioSeg test (In-domain)gIoU: 51.4 -> 52.8Improved
train with RL instead of SFT (ablation)VisionReasoner · SocioSeg OOD (New Region)gIoU: 24.7 -> 34.4Improved
train with RL instead of SFT (ablation)VisionReasoner · SocioSeg OOD (Map Style)gIoU: 40.9 -> 44.4Improved
replace VisionReasoner single-stage with SocioReasoner two-stageVisionReasoner · SocioSeg test (All dataset)cIoU: 44.0 -> 47.9Improved
remove frozen CLIP-based open-vocabulary approach (SegEarth-OV) vs trained reasoning VLMSegEarth-OV · SocioSeg test (All dataset)gIoU: 3.7 vs 52.8Hurt

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