Name
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. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICIP40778.2020.9191201 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Feature disentanglement, anomaly detection, generative model | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wei-Yu Lee | 1 | 0 | 0.68 |
| Yu-Chiang Frank Wang | 2 | 914 | 61.63 |