AI Paper Atlas

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

Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs

Zhikang Xu, Qianqian Xu, Zitai Wang, Cong Hua, Sicong Li, Zhiyong Yang, Qingming Huang

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 1 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
select negative texts by inter-modal distance instead of intra-modal distance (ablation)NegLabel · ImageNet-1k Four-OOD avgFPR95: 25.40 -> 24.12Improved
add inter-modal guided extra negative embeddings from inverted OOD images (ablation)Intra SNT · ImageNet-1k Four-OOD avgFPR95: 25.40 -> 14.76Improved
use inter-modal instead of intra-modal filtering of extra negative embeddings (ablation)InterNeg with Inter SNT · ImageNet-1k Four-OOD avgFPR95: 19.99 -> 14.04Improved
use inter-modal selection for negative texts on top of inter-modal extra embeddings (ablation)InterNeg · ImageNet-1k Four-OOD avgFPR95: 14.76 -> 14.04Improved
InterNeg vs best prior zero-shot method AdaNegCLIP ViT-B/16 · ImageNet-1k Four-OOD avgFPR95: 18.92 -> 14.04Improved
InterNeg vs AdaNeg on harder benchmarkCLIP ViT-B/16 · ImageNet-1k OpenOOD Near-OODAUROC: 76.70 -> 82.20Improved
use only one ID image per class as proxy (ablation)InterNeg · ImageNet-1k Four-OODAUROC/FPR95Hurt
increase K beyond M=2000 (ablation)InterNeg · Four-OOD and Near-OODOOD detection performanceHurt
vary high-confidence threshold beta (ablation)InterNeg · Four-OOD and Near-OODOOD detection performanceNo clear effect

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