Hyperspectral anomaly detection via memory‐augmented autoencoders
Abstract Recently, the autoencoder (AE) based method plays a critical role in the hyperspectral anomaly detection domain. However, due to the strong generalised capacity of AE, the abnormal samples are usually reconstructed well along with the normal background samples. Thus, in order to separate an...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12116 |
| _version_ | 1797383470307082240 |
|---|---|
| author | Zhe Zhao Bangyong Sun |
| author_facet | Zhe Zhao Bangyong Sun |
| author_sort | Zhe Zhao |
| collection | DOAJ |
| description | Abstract Recently, the autoencoder (AE) based method plays a critical role in the hyperspectral anomaly detection domain. However, due to the strong generalised capacity of AE, the abnormal samples are usually reconstructed well along with the normal background samples. Thus, in order to separate anomalies from the background by calculating reconstruction errors, it can be greatly beneficial to reduce the AE capability for abnormal sample reconstruction while maintaining the background reconstruction performance. A memory‐augmented autoencoder for hyperspectral anomaly detection (MAENet) is proposed to address this challenging problem. Specifically, the proposed MAENet mainly consists of an encoder, a memory module, and a decoder. First, the encoder transforms the original hyperspectral data into the low‐dimensional latent representation. Then, the latent representation is utilised to retrieve the most relevant matrix items in the memory matrix, and the retrieved matrix items will be used to replace the latent representation from the encoder. Finally, the decoder is used to reconstruct the input hyperspectral data using the retrieved memory items. With this strategy, the background can still be reconstructed well while the abnormal samples cannot. Experiments conducted on five real hyperspectral anomaly data sets demonstrate the superiority of the proposed method. |
| first_indexed | 2024-03-08T21:21:27Z |
| format | Article |
| id | doaj.art-963ff4ff38e94c128963e13eda739cae |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-03-08T21:21:27Z |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-963ff4ff38e94c128963e13eda739cae2023-12-21T09:45:29ZengWileyCAAI Transactions on Intelligence Technology2468-23222023-12-01841274128710.1049/cit2.12116Hyperspectral anomaly detection via memory‐augmented autoencodersZhe Zhao0Bangyong Sun1Faculty of Printing, Packaging Engineering and Digital Media Technology Xi'an University of Technology Xi'an ChinaFaculty of Printing, Packaging Engineering and Digital Media Technology Xi'an University of Technology Xi'an ChinaAbstract Recently, the autoencoder (AE) based method plays a critical role in the hyperspectral anomaly detection domain. However, due to the strong generalised capacity of AE, the abnormal samples are usually reconstructed well along with the normal background samples. Thus, in order to separate anomalies from the background by calculating reconstruction errors, it can be greatly beneficial to reduce the AE capability for abnormal sample reconstruction while maintaining the background reconstruction performance. A memory‐augmented autoencoder for hyperspectral anomaly detection (MAENet) is proposed to address this challenging problem. Specifically, the proposed MAENet mainly consists of an encoder, a memory module, and a decoder. First, the encoder transforms the original hyperspectral data into the low‐dimensional latent representation. Then, the latent representation is utilised to retrieve the most relevant matrix items in the memory matrix, and the retrieved matrix items will be used to replace the latent representation from the encoder. Finally, the decoder is used to reconstruct the input hyperspectral data using the retrieved memory items. With this strategy, the background can still be reconstructed well while the abnormal samples cannot. Experiments conducted on five real hyperspectral anomaly data sets demonstrate the superiority of the proposed method.https://doi.org/10.1049/cit2.12116anomaly detectionhyperspectral imagesmemory autoencoder |
| spellingShingle | Zhe Zhao Bangyong Sun Hyperspectral anomaly detection via memory‐augmented autoencoders CAAI Transactions on Intelligence Technology anomaly detection hyperspectral images memory autoencoder |
| title | Hyperspectral anomaly detection via memory‐augmented autoencoders |
| title_full | Hyperspectral anomaly detection via memory‐augmented autoencoders |
| title_fullStr | Hyperspectral anomaly detection via memory‐augmented autoencoders |
| title_full_unstemmed | Hyperspectral anomaly detection via memory‐augmented autoencoders |
| title_short | Hyperspectral anomaly detection via memory‐augmented autoencoders |
| title_sort | hyperspectral anomaly detection via memory augmented autoencoders |
| topic | anomaly detection hyperspectral images memory autoencoder |
| url | https://doi.org/10.1049/cit2.12116 |
| work_keys_str_mv | AT zhezhao hyperspectralanomalydetectionviamemoryaugmentedautoencoders AT bangyongsun hyperspectralanomalydetectionviamemoryaugmentedautoencoders |