One-Class Novelty Detection via Sparse Representation with Contrastive Deep Features

Kuang Ting Lee, Chien Yu Chiou, Chun Rong Huang

研究成果: Conference contribution同行評審

1 引文 斯高帕斯(Scopus)

摘要

We propose a novel one-class novelty detection method by using sparse representation with contrastive deep features. To learn representative deep features from target one- class training data, we generate in-class and pseudo out-of-class training samples at first. Then, shared-weight networks with the contrastive loss are used to learn the contrastive deep features based on the generated training samples. We model the distribution of the learned features of the target class by using sparse dictionary learning. Testing samples are identified based on sparse reconstruction results by using the learned dictionary. The experimental results show the performance of the proposed method is comparable with state-of-the-art methods in the MNIST dataset and outperforms those methods in the CIFAR- 10 dataset.

原文English
主出版物標題Proceedings - 2020 International Computer Symposium, ICS 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面61-66
頁數6
ISBN(電子)9781728192550
DOIs
出版狀態Published - 12月 2020
事件2020 International Computer Symposium, ICS 2020 - Tainan, Taiwan
持續時間: 17 12月 202019 12月 2020

出版系列

名字Proceedings - 2020 International Computer Symposium, ICS 2020

Conference

Conference2020 International Computer Symposium, ICS 2020
國家/地區Taiwan
城市Tainan
期間17/12/2019/12/20

指紋

深入研究「One-Class Novelty Detection via Sparse Representation with Contrastive Deep Features」主題。共同形成了獨特的指紋。

引用此