Language-Free Universal Vision Anomaly Detection

[AAAI 2026] 中文公众号报道

Implementation of CVPR'23 paper "WinCLIP: Zero-/few-shot anomaly classification and segmentation". It successfully reproduces the same zero-/few-shot AD performance as that in the original paper.

Official PyTorch implementation of KDD2025 paper "AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection"

Official PyTorch implementation of ICCV'25 paper "Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection".

Official Code for IJCAI25 paper "Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts"

[CVPR'26] AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

LECLIP : Boosting Zero-Shot Anomaly Detection with Local Enhanced CLIP

Reviews of papers on image anomaly detection | prompt learning | etc

Official implementation for paper "Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection" (ICLR 2024)

Evaluation framework for MLLMs on the Odd-One-Out task. Benchmarking spatial reasoning, relational logic, zero-shot anomaly detection in complex multi-object scenes.