DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup | AD Research Hub

AD Research Hub

Dashboard People Papers Workshops Datasets Research Map

⌘K

AD Research Hub — Anomaly Detection in Computer Vision

← Back to Papers

DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

Authors

Zhen Qu, Xian Tao, Xinyi Gong, ShiChen Qu, Xiaopei Zhang, Xingang Wang, Fei Shen, Zhengtao Zhang, Mukesh Prasad, Guiguang Ding

ICCV-2025direct anomaly

Score

13

Tags

anomaly segmentation

Methods

CLIPSelf-supervisedFew-shot

Links

Paper Page arXiv Abstract arXiv PDF

Cite

Related Papers

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

Alexey Nekrasov, Malcolm Burdorf, Stewart Worrall +2

CVPR-2025direct anomaly13

anomaly segmentation

Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet

Komal Kumar, Snehashis Chakraborty, Dwarikanath Mahapatra +2

WACV-2025direct anomaly13

anomaly segmentation

ViTSelf-supervisedMVTec

PDF

Towards Accurate Unified Anomaly Segmentation

Wenxin Ma, Qingsong Yao, Xiang Zhang +3

WACV-2025direct anomaly13

anomaly segmentation

MVTecMVTec-AD

G2SF: Geometry-Guided Score Fusion for Multimodal Industrial Anomaly Detection

Chengyu Tao, Xuanming Cao, Juan Du

ICCV-2025direct anomaly24

anomaly detectionindustrial anomaly

PDF

Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection

Giacomo D' Amicantonio, Snehashis Majhi, Quan Kong +4

ICCV-2025direct anomaly24

anomaly detectionvideo anomaly

PDF

RareCLIP: Rarity-aware Online Zero-shot Industrial Anomaly Detection

Jianfang He, Min Cao, Silong Peng +1

ICCV-2025direct anomaly24

anomaly detectionindustrial anomaly

CLIPZero-shot

PDF

Sign in to access this content