AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models

Yingjie Zhang, Shuai Li, Peng Wang

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 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 NegA training and NegS scoring with LLM negative labelsYOLO-World · VOC vs OpenImagesFPR95: 48.8 -> 23.3Improved
add NegA training and NegS scoringYOLO-World · VOC vs OpenImagesAUROC: 81.4 -> 92.6Improved
add negative-label guided attention and scoring on ID detectionYOLO-World + CoOp · VOC (ID detection)mAP (ID): 72.2 -> 72.5No clear effect
generate negative labels with an LLM instead of lexical corpus mining (ablation)NegAS · VOC vs OpenImagesFPR95: 42.4 -> 23.3Improved
generate negative labels with an LLM instead of lexical corpus mining (ablation)NegAS · VOC vs MS-COCOFPR95: 11.7 -> 9.9Improved
swap closed-source LLM for open-source Qwen3 to generate negative labels (ablation)NegAS · VOC vs MS-COCOFPR95: 9.9 -> 9.9 (AUROC 95.8)No clear effect
add NegS scoring to the CoOp YOLO-World baseline (ablation)YOLO-World + CoOp · VOC vs OOD setsFPR95 / AUROCImproved
add NegA on top of NegS (ablation)YOLO-World + CoOp · VOC vs OOD setsFPR95 / AUROCImproved
add Gaussian noise to negative label embeddings (ablation)NegAS · VOC vs OpenImagesFPR95Improved
restrict OOD loss to background regions (ablation)NegAS · VOC vs OOD setsOOD detectionImproved
set OOD loss coefficient alpha to 3 (ablation)NegAS · VOC vs OOD setsOOD detectionImproved

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