2021/01/07 by Sungkwon An, An, Sungkwon, Jeonghoon Kim +7
Computer Science · Mathematics · Medicine · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Data-Driven Disease Surveillance #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Seismology and Earthquake Studies #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2101.02358
Accepted to AAAI 2021 Workshop: Towards Robust, Secure and Efficient Machine Learning
arxiv created 2021/01/07 · openalex publication_date 2021/01/07 · arxiv updated 2021/01/08 · openalex created_date 2021/01/18 · openalex updated_date 2026/07/28
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of different features other than class information which makes models hard to detect novelty data. The problem gets harder in multi-modal normality case. To address this challenge, we propose a new way of measuring novelty score in multi-modal normality cases using orthogonalized latent space. Specifically, we employ orthogonal low-rank embedding in the latent space to disentangle the features in the latent space using mutual class information. With the orthogonalized latent space, novelty score is defined by the change of each latent vector. Proposed algorithm was compared to state-of-the-art novelty detection algorithms using GAN such as RaPP and OCGAN, and experimental results show that ours outperforms those algorithms.