This repository serves as a comprehensive, community-driven collection of literature and resources for deep learning-based anomaly detection. It aims to systematically organize research papers, datasets, and benchmarks, providing a valuable reference for researchers and practitioners in the field.

How It Works

The repository categorizes anomaly detection techniques by methodology (e.g., AutoEncoder, GAN, Transformer, Diffusion Models), mechanism (e.g., Dataset, Benchmark, Loss Function), and application domain (e.g., Finance, Medical Image, Autonomous Driving). This structured approach allows users to easily navigate and discover relevant research across various facets of anomaly detection.

Quick Start & Requirements

This repository is a curated collection of papers and resources, not a software library. No installation or specific requirements are needed to browse its content.

Highlighted Details

• Extensive categorization of deep learning methodologies for anomaly detection.
• Broad coverage of application domains, from finance to autonomous driving.
• Includes links to numerous survey papers and specific research articles.
• Organizes resources by mechanism, such as datasets, benchmarks, and loss functions.

Maintenance & Community

The repository is maintained by Chunyang Zhang, who is actively seeking collaborators to help update and expand its content. Contributions are welcomed via pull requests or issues.

Licensing & Compatibility

The repository itself does not specify a license, but it links to external research papers, each with its own licensing.

Limitations & Caveats

As a literature collection, this repository does not provide executable code or pre-trained models. Its value is in its comprehensive cataloging of existing research.