AI Paper Atlas

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

UNI-OOD: Unified Object- and Image-level Out-of-Distribution Detection via Cross-Context Attentive Vision-Language Modeling

Yuchuan Li, Azadeh Motamedi, Hyock Ju Kwon, Chul B Park, Il-Min Kim

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection

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
build background text embedding with inter-text attention instead of comma-separated labels (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 93.21 -> 98.52Improved
use inter-text attention instead of averaging individual text embeddings (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 95.05 -> 98.52Improved
use inter-text attention instead of MLP combination (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 97.20 -> 98.52Improved
add inter-image attention for background (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 96.02 -> 98.52Improved
add background text-vision alignment (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 96.67 -> 98.52Improved
add intra-image attention for the target object (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 95.72 -> 98.52Improved
add target text-vision alignment (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 96.35 -> 98.52Improved
add CNNs to the combiner for patch embeddings (ablation)UNI-OOD · Object-level BDD-100k / OpenImagesAUROC: 97.14 -> 98.52Improved
add intra-image attention (ablation)UNI-OOD · Image-level ImageNet-1k / SUNAUROC: 95.31 -> 97.35Improved
add inter-image attention (ablation)UNI-OOD · Image-level ImageNet-1k / iNaturalistFPR95: 11.86 -> 4.92Improved
add CNNs to the combiner (ablation)UNI-OOD · Image-level ImageNet-1k / PLACESAUROC: 93.75 -> 94.27Improved
use unified UNI-OOD instead of RUNAobject-level OOD detection · PASCAL-VOC / MS-COCOAUROC: 92.92 -> 95.07Improved

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