AI Paper Atlas

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

Vision-Language Dual-Pattern Matching for Out-of-Distribution Detection

Zihan Zhang, Zhuo Xu, Xiang Xiang

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 3 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 visual pattern matching (KL) to textual matching (ablation)DPM-F · CIFAR-100 ID, LSUN OOD (ViT-B-32)AUROC: 87.71 -> 95.41Improved
use KL divergence rather than euclidean distance for visual matching (ablation)DPM-F · CIFAR-100 ID, CIFAR-10 OODAUROC: 61.54 -> 78.72Improved
add linear projection layers to learnable modules (ablation)DPM-T · CIFAR-100 (ViT-B-32)AUROC: 84.99 -> 92.63Improved
add domain-specific feature aggregation (DSFA) on top of prompt and projection (ablation)DPM-T · CIFAR-100 (ViT-B-32)AUROC: 92.63 -> 94.79Improved
add DSFA alone without prompt or projection (ablation)DPM-F · CIFAR-100 (ViT-B-32)AUROC: 84.14 -> 76.93Hurt
combine L_VM and L_TM losses instead of L_org alone (ablation)DPM-T · CIFAR-100 (ViT-B-16)AUROC: 86.65 -> 91.62Improved
add L_org loss to L_VM + L_TM (ablation)DPM-T · CIFAR-100 (ViT-B-16)AUROC: 91.62 -> 91.07Hurt
use L_TM alone without L_VM (ablation)DPM-T · CIFAR-100 (ViT-B-16)AUROC: 61.14 vs 91.62Hurt
set feature aggregation factor gamma to 0.7 instead of 0 (ablation)DPM-F · CIFAR-100 (ViT-B-16)AUROC: about 8% AUROC improvementImproved
increase trainset samples per class (ablation)DPM-F · CIFAR-100 (ViT-B-16)mean AUROC: 78.44 -> 85.33 (5 -> 500 per class)Improved
use DPM-F over MCM under covariate shift (ImageNet-A as OOD)CLIP OOD detection · ImageNet val ID, ImageNet-A OODAUROC: 80.74 -> 86.76Improved
add lightweight training (DPM-T over DPM-F)DPM · ImageNet-1k, ViT-B-16AUROC: 92.78 -> 95.72Improved

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