Anomaly Detection in Aerial Images VIA Semi-Supervised Adversarial Training

Chih Chang Yu, Pu Hsin Wang, Hsu Yung Cheng

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Most of the deep neural networks require a large amount of data for training to achieve good results. However, in practical anomaly detection applications, we usually only have few labeled anomalous samples that have various types. This study proposed an innovative hybrid architecture that aims to detect anomalies with a small number of labeled anomalous samples. The proposed method consists of two stages. First, the network learns the distribution of normal data with a generative adversarial network (GAN). Second, the discriminator of the network is combined with a classifier and the training process updates different network components depending on whether the labeled samples are normal or anomalies. From the experiments on CIFAR-10 and UC Merced datasets, we demonstrate that our method yields significant performance improvements then another GAN-based approach even when few labeled samples are provided.

原文???core.languages.en_GB???
主出版物標題IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
發行者Institute of Electrical and Electronics Engineers Inc.
頁面5035-5038
頁數4
ISBN(電子)9781665427920
DOIs
出版狀態已出版 - 2022
事件2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, Malaysia
持續時間: 17 7月 202222 7月 2022

出版系列

名字International Geoscience and Remote Sensing Symposium (IGARSS)
2022-July

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
國家/地區Malaysia
城市Kuala Lumpur
期間17/07/2222/07/22

指紋

深入研究「Anomaly Detection in Aerial Images VIA Semi-Supervised Adversarial Training」主題。共同形成了獨特的指紋。

引用此