image-anomaly-detection

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

ADRepository: Real-world anomaly detection datasets, including tabular data (categorical and numerical data), time series data, graph data, image data, and video data.

Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.

Official implementation of CVPR'24 paper 'Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection'.

Official PyTorch implementation of the ICCV'23 paper “Anomaly Detection under Distribution Shift”

A toolbox for Python Anomaly [Outlier] Detection. This toolbox covers from traditional machine learning approaches to deep learning based approaches for image anomaly detection.

Convolutional autoencoder-based anomaly detection vs shallow baselines — IEEE IJCNN 2024. Live demo on HuggingFace Spaces.

ADer is an open source visual anomaly detection toolbox based on PyTorch, which supports multiple popular AD datasets and approaches.