AI Paper Atlas

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

CURE: Contextual Debiasing and Unbiased Refinement for Training-Free Open-Vocabulary Semantic Segmentation

Jiean Wang, Sanqing Qu, Fan Lu, Huanhuan Bao, Wei Tian, Bo Jin, Jiangtong Li, Junqiao Zhao, Guang Chen

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 0 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 Reject and Reconstruct (RR) (ablation)ClearCLIP · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 28.2 -> 28.9Improved
add Global Contextual Debiasing (GCD) (ablation)ClearCLIP · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 28.2 -> 29.1Improved
add Spatial Correlation Refinement (SCR) (ablation)ClearCLIP · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 28.2 -> 29.4Improved
add SCR on top of RR and GCD (ablation)CURE (RR+GCD) · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 29.5 -> 30.9Improved
add RR on top of GCD and SCR (ablation)CURE (GCD+SCR) · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 30.6 -> 30.9Improved
replace direct CLS subtraction with GCD (ablation)CURE · ADE20K/PC59/Cityscapes avg (ViT-B/16)mIoU (%): 29.8 -> 30.9Improved
add CURE to ClearCLIPClearCLIP (ViT-B/16) · 5-dataset average (VOC20, PC59, ADE20K, Cityscapes, COCO-Stuff)mIoU (%): 37.9 -> 40.1Improved
add CURE to ClearCLIPClearCLIP (ViT-L/14) · 5-dataset average (VOC20, PC59, ADE20K, Cityscapes, COCO-Stuff)mIoU (%): 35.3 -> 39.6Improved
add CURE to SCLIPSCLIP (ViT-L/14) · 5-dataset average (VOC20, PC59, ADE20K, Cityscapes, COCO-Stuff)mIoU (%): 24.4 -> 40.1Improved
add CURE to SCCLIPSCCLIP (ViT-B/16) · 5-dataset average (VOC20, PC59, ADE20K, Cityscapes, COCO-Stuff)mIoU (%): 42.4 -> 42.9Improved
add CURE to ClearCLIP with MetaCLIP pretrainingClearCLIP · ADE20K/COCO/PC59 avgmIoU (%): 25.2 -> 27.6Improved
add CURE to ClearCLIP on long-tail classesClearCLIP · Cityscapes long-tailmIoU (%): 26.4 -> 27.1Improved

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