Learning Disentangled Feature Representations for Anomaly Detection
Journal
Proceedings - International Conference on Image Processing, ICIP
Journal Volume
2020-October
Pages
2156-2160
Date Issued
2020
Author(s)
Lee W.-Y
Abstract
Anomaly detection is a challenging task that requires identifying anomalous data by observing only normal data during training. Previous works typically approached this problem by assessing data recovery with properly selected thresholds. However, the performance would be affected by content variants or background clutter. Hence, in this paper, we propose a novel deep learning based method, which learns disentangled feature representations for separating semantic and visual appearance information, so that the anomaly of the input data can be determined based on its semantic features. Our qualitative results demonstrate the feasibility of the feature disentanglement, and the quantitative experiments confirm that our method outperforms other methods. ? 2020 IEEE.
Subjects
Deep learning; Image processing; Semantics; Background clutter; Data recovery; Feature representation; Input datas; Learning-based methods; Quantitative experiments; Semantic features; Visual appearance; Anomaly detection
SDGs
Type
conference paper