AI Paper Atlas

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

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Tao Gong, Qi Chu, Bin Liu, Wei Zhou, Nenghai Yu

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 12 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 FFE adapter instead of a plain conv adapter (ablation)CLIP · MVTec AD image-levelAUROC: 87.8 -> 90.0Improved
add LFS adapter instead of a plain conv adapter (ablation)CLIP · MVTec AD image-levelAUROC: 87.8 -> 90.6Improved
add LFS adapter instead of a plain conv adapter (ablation)CLIP · VisA image-levelAUROC: 82.3 -> 83.9Improved
add FFE adapter instead of a plain conv adapter (ablation)CLIP · VisA pixel-levelAUROC: 94.8 -> 95.1Improved
combine FFE and LFS adapters (add LFS to FFE) (ablation)FE-CLIP · MVTec AD image-levelAUROC: 90.0 -> 91.9Improved
combine FFE and LFS adapters (add FFE to LFS) (ablation)FE-CLIP · MVTec AD image-levelAUROC: 90.6 -> 91.9Improved
combine FFE and LFS adapters (ablation)FE-CLIP · VisA pixel-levelAUROC: 95.5 -> 95.9Improved
combine FFE and LFS adapters (ablation)FE-CLIP · MVTec AD pixel-levelAUROC: 91.5 -> 92.6Improved
use DCT instead of FFT for frequency transform (ablation)FE-CLIP · MVTec AD image-levelAUROC: 92.0 -> 91.9No clear effect
use DCT instead of FFT for frequency transform (ablation)FE-CLIP · VisA image-levelAUROC: 84.1 -> 84.6No clear effect
use DCT instead of FFT for frequency transform (ablation)FE-CLIP · MVTec AD pixel-levelAUROC: 92.8 -> 92.6No clear effect
add more normal shots (1 to 4)FE-CLIP · MVTec AD image-level few-shotAUROC: 95.6 -> 96.6Improved

Later papers that compared with this method

1 later accepted paper reports FE-CLIP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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