AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models

Yuanwei Hu, Bo Peng, Yadan Luo, Zhen Fang, Ling Chen, Jie Lu

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class 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
learn visual-space prototypes online instead of text-as-prototype with adaptive negative cache (vs AdaNeg+NegLabel)NegLabel pipeline on CLIP ViT-B/16 · ImageNet-1K, 4 OOD sets averageFPR95: 18.92 -> 12.79Improved
online visual prototype learning vs AdaNeg+NegLabel on CIFAR-100 Near-OODNegLabel pipeline · OpenOOD CIFAR-100 ID, Near-OODFPR95: 59.07 -> 45.70Improved
online visual prototype learning vs AdaNeg+NegLabel on ImageNet Near-OODNegLabel pipeline · OpenOOD ImageNet-1K ID, Near-OODFPR95: 67.51 -> 52.86Improved
swap visual encoder from ResNet50 to ViT-B/32 to ViT-L/14 (ablation)Ours · ImageNet-1K, 4 OOD sets averageFPR95: 15.88 -> 15.11 -> 12.12Improved
increase input resolution to 336x336 (ablation)Ours with ViT-L/14 · ImageNet-1K, 4 OOD sets averageFPR95: 12.12 -> 11.21Improved
vary kappa, rho and beta hyper-parameters (ablation)Ours · ImageNet-1KFPR95No clear effect
use LAPT learned prompts instead of pre-defined prompt (ablation)Ours · ImageNet-1KFPR95: 12.79 -> 10.16Improved
apply method under domain-shifted ID data (ImageNet-A)Ours · ImageNet-A as IDFPR95: 35.30 -> 20.99Improved
online visual prototypes on ImageNet-R iNaturalist subsetOurs · ImageNet-R as ID, iNaturalistFPR95: 0.89 -> 1.12Hurt

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