Complex Background Reconstruction for Novelty Detection
Novelty detection aims to detect samples from classes different from the training samples (i.e., the normal class). Existing approaches predominantly make the target reconstruction better and choose the appropriate reconstruction error measurement method but ignore the influence of background inform...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/19/10702 |
| _version_ | 1797576229247778816 |
|---|---|
| author | Kun Zhao Man Su Ran An Hui He Zhi Wang |
| author_facet | Kun Zhao Man Su Ran An Hui He Zhi Wang |
| author_sort | Kun Zhao |
| collection | DOAJ |
| description | Novelty detection aims to detect samples from classes different from the training samples (i.e., the normal class). Existing approaches predominantly make the target reconstruction better and choose the appropriate reconstruction error measurement method but ignore the influence of background information on this process. This paper proposes a novel reconstruction network and mutual information Siamese network. The reconstructed network aims to make the distribution of reconstructed samples consistent with that of original samples, intending to reduce background interference in the reconstruction process. After this, we measure the distance between the original and generated images based on a mutual information Siamese network, which extracts more discriminative features to calculate the similarity between the original images and their reconstructed ones. This part of the network uses global context information to improve the detection accuracy. We conduct extreme experiments to evaluate the proposed solution on two challenging public datasets. The experimental results show that the proposed method significantly outperforms the state-of-the-art methods. |
| first_indexed | 2024-03-10T21:49:19Z |
| format | Article |
| id | doaj.art-299cb121a5b34157a614a9b76694ca33 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:49:19Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-299cb121a5b34157a614a9b76694ca332023-11-19T14:03:00ZengMDPI AGApplied Sciences2076-34172023-09-0113191070210.3390/app131910702Complex Background Reconstruction for Novelty DetectionKun Zhao0Man Su1Ran An2Hui He3Zhi Wang4The School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaBeijing Institute of Tracking and Telecommunication Technology, Beijing 100094, ChinaThe School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaThe School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaThe School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaNovelty detection aims to detect samples from classes different from the training samples (i.e., the normal class). Existing approaches predominantly make the target reconstruction better and choose the appropriate reconstruction error measurement method but ignore the influence of background information on this process. This paper proposes a novel reconstruction network and mutual information Siamese network. The reconstructed network aims to make the distribution of reconstructed samples consistent with that of original samples, intending to reduce background interference in the reconstruction process. After this, we measure the distance between the original and generated images based on a mutual information Siamese network, which extracts more discriminative features to calculate the similarity between the original images and their reconstructed ones. This part of the network uses global context information to improve the detection accuracy. We conduct extreme experiments to evaluate the proposed solution on two challenging public datasets. The experimental results show that the proposed method significantly outperforms the state-of-the-art methods.https://www.mdpi.com/2076-3417/13/19/10702figure reconstructionone-class novelty detectionmutual information fusion |
| spellingShingle | Kun Zhao Man Su Ran An Hui He Zhi Wang Complex Background Reconstruction for Novelty Detection Applied Sciences figure reconstruction one-class novelty detection mutual information fusion |
| title | Complex Background Reconstruction for Novelty Detection |
| title_full | Complex Background Reconstruction for Novelty Detection |
| title_fullStr | Complex Background Reconstruction for Novelty Detection |
| title_full_unstemmed | Complex Background Reconstruction for Novelty Detection |
| title_short | Complex Background Reconstruction for Novelty Detection |
| title_sort | complex background reconstruction for novelty detection |
| topic | figure reconstruction one-class novelty detection mutual information fusion |
| url | https://www.mdpi.com/2076-3417/13/19/10702 |
| work_keys_str_mv | AT kunzhao complexbackgroundreconstructionfornoveltydetection AT mansu complexbackgroundreconstructionfornoveltydetection AT ranan complexbackgroundreconstructionfornoveltydetection AT huihe complexbackgroundreconstructionfornoveltydetection AT zhiwang complexbackgroundreconstructionfornoveltydetection |