AI Paper Atlas

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

VarProtoAD: Variational Prototype-Conditioned Prompting for Zero-Shot Anomaly Detection

Mengyang Zhao, Zhuolin He, Haiyang Yu, Teng Fu, Ke Niu, Xiangyang Xue

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 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 K-means prototypes (ablation)prompt-only ZSAD · VisA image-levelAUROC: 85.4 -> 89.1Improved
add variational vMF prototypes (ablation)prompt-only ZSAD · VisA image-levelAUROC: 85.4 -> 90.0Improved
add variational vMF prototypes (ablation)prompt-only ZSAD · VisA pixel-levelAUROC: 95.2 -> 96.3Improved
add variational vMF prototypes (ablation)prompt-only ZSAD · ColonDB pixel-levelAUROC: 84.5 -> 88.3Improved
use vMF instead of K-means prototypes (ablation)VarProtoAD · ColonDB pixel-levelAUROC: 87.2 -> 88.3Improved
add ungated cross-attention conditioning (ablation)prompt-only ZSAD · VisA image-levelAUROC: 85.4 -> 88.2Improved
add scalar gate to cross-attention (ablation)cross-attn conditioning · VisA image-levelAUROC: 88.2 -> 88.7Improved
use confidence-dependent gate instead of scalar gate (ablation)cross-attn conditioning · VisA image-levelAUROC: 88.7 -> 90.0Improved
add implicit deviation prompts to explicit prompts (ablation)VarProtoAD · VisA image-levelAUROC: 89.2 -> 90.0Improved
add explicit abnormal prompts to implicit prompts (ablation)VarProtoAD · VisA image-levelAUROC: 89.1 -> 90.0Improved
explicit-only vs implicit-only abnormal prompts (ablation)VarProtoAD · VisA image-levelAUROC: 89.2 vs 89.1No clear effect
use VarProtoAD instead of Bayes-PFLZSAD methods · 15 datasets overall image-levelAUROC: 94.7 -> 95.6Improved

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