ESAD: End-to-end Deep Semi-supervised Anomaly Detection
This work provides a more practical and effective solution for anomaly detection in real-world scenarios where some labeled data is available, benefiting fields like medical diagnosis.
This paper addresses semi-supervised anomaly detection, where a small set of labeled samples are available. The authors propose a new KL-divergence based objective function and a novel encoder-decoder-encoder architecture, demonstrating significant performance improvements over state-of-the-art methods on medical diagnosis and other anomaly detection benchmarks.
This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small additional set of labeled samples are provided. We propose a new KL-divergence based objective function for semi-supervised anomaly detection, and show that two factors: the mutual information between the data and latent representations, and the entropy of latent representations, constitute an integral objective function for anomaly detection. To resolve the contradiction in simultaneously optimizing the two factors, we propose a novel encoder-decoder-encoder structure, with the first encoder focusing on optimizing the mutual information and the second encoder focusing on optimizing the entropy. The two encoders are enforced to share similar encoding with a consistent constraint on their latent representations. Extensive experiments have revealed that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, including medical diagnosis and several classic anomaly detection benchmarks.