ADBench: Anomaly Detection Benchmark

By Songqiao Han, Xiyang Hu, Hailiang Huang, Mingqi Jiang, Yue Zhao. Neural Information Processing Systems, 2022

463 citations recorded by the source corpus.

Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? In this work, we answer these key questions by conducting (to our best knowledge) the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench. Our extensive experiments (98,436 in total) identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design. With ADBench, researchers can easily conduct comprehensive and fair evaluations for newly proposed methods on the datasets (including our contributed ones from natural language and computer vision domains) against the existing baselines. To foster accessibility and reproducibility, we fully open-source ADBench and the corresponding results.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0bff4af924788d9779041513b6894385eac51ffd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ziwei Liu
2. Yixuan Li
3. Kaiyang Zhou
4. Jingkang Yang
5. Wayne Zhang
6. Haoqi Wang
7. Bo Li
8. Yiyou Sun

In Computer Networks and Communications

1. Yixuan Li
2. Wayne Zhang
3. Haoqi Wang
4. Bo Li
5. Ming-Hsuan Yang
6. Ziwei Liu
7. Jingkang Yang
8. Dan Hendrycks

In Signal Processing

1. Yixuan Li
2. Ming-Hsuan Yang
3. Wayne Zhang
4. Haoqi Wang
5. Ziwei Liu
6. Guangyao Chen
7. Jingkang Yang
8. Dan Hendrycks

Citations in the corpus

• OpenOOD: Benchmarking Generalized Out-of-Distribution Detection (2022, background): “Current anomaly detection settings often restrict the in-distribution (normality) to be with a single class [35].”
• Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “Generative models have been shown to own a powerful mechanism for anomaly detection [70, 87, 252], modeling normal or healthy reference data.”