Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex
Edge detection is of great importance to the middle and high-level vision task in computer vision, and it is useful to improve its performance. This paper is different from previous edge detection methods designed only for decoding networks. We propose a new edge detection network composed of modula...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.1073484/full |
| _version_ | 1828092964866359296 |
|---|---|
| author | Zhenguang Zhang Chuan Lin Yakun Qiao Yongcai Pan |
| author_facet | Zhenguang Zhang Chuan Lin Yakun Qiao Yongcai Pan |
| author_sort | Zhenguang Zhang |
| collection | DOAJ |
| description | Edge detection is of great importance to the middle and high-level vision task in computer vision, and it is useful to improve its performance. This paper is different from previous edge detection methods designed only for decoding networks. We propose a new edge detection network composed of modulation coding network and decoding network. Among them, modulation coding network is the combination of modulation enhancement network and coding network designed by using the self-attention mechanism in Transformer, which is inspired by the selective attention mechanism of V1, V2, and V4 in biological vision. The modulation enhancement network effectively enhances the feature extraction ability of the encoding network, realizes the selective extraction of the global features of the input image, and improves the performance of the entire model. In addition, we designed a new decoding network based on the function of integrating feature information in the IT layer of the biological vision system. Unlike previous decoding networks, it combines top-down decoding and bottom-up decoding, uses down-sampling decoding to extract more features, and then achieves better performance by fusing up-sampling decoding features. We evaluated the proposed method experimentally on multiple publicly available datasets BSDS500, NYUD-V2, and barcelona images for perceptual edge detection (BIPED). Among them, the best performance is achieved on the NYUD and BIPED datasets, and the second result is achieved on the BSDS500. Experimental results show that this method is highly competitive among all methods. |
| first_indexed | 2024-04-11T06:37:23Z |
| format | Article |
| id | doaj.art-bee7895edf8c433bb35fe27204f50beb |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-11T06:37:23Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-bee7895edf8c433bb35fe27204f50beb2022-12-22T04:39:40ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-11-011610.3389/fnins.2022.10734841073484Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortexZhenguang ZhangChuan LinYakun QiaoYongcai PanEdge detection is of great importance to the middle and high-level vision task in computer vision, and it is useful to improve its performance. This paper is different from previous edge detection methods designed only for decoding networks. We propose a new edge detection network composed of modulation coding network and decoding network. Among them, modulation coding network is the combination of modulation enhancement network and coding network designed by using the self-attention mechanism in Transformer, which is inspired by the selective attention mechanism of V1, V2, and V4 in biological vision. The modulation enhancement network effectively enhances the feature extraction ability of the encoding network, realizes the selective extraction of the global features of the input image, and improves the performance of the entire model. In addition, we designed a new decoding network based on the function of integrating feature information in the IT layer of the biological vision system. Unlike previous decoding networks, it combines top-down decoding and bottom-up decoding, uses down-sampling decoding to extract more features, and then achieves better performance by fusing up-sampling decoding features. We evaluated the proposed method experimentally on multiple publicly available datasets BSDS500, NYUD-V2, and barcelona images for perceptual edge detection (BIPED). Among them, the best performance is achieved on the NYUD and BIPED datasets, and the second result is achieved on the BSDS500. Experimental results show that this method is highly competitive among all methods.https://www.frontiersin.org/articles/10.3389/fnins.2022.1073484/fulledge detectionbiological visionvisual cortexself-attention mechanismconvolutional neural network |
| spellingShingle | Zhenguang Zhang Chuan Lin Yakun Qiao Yongcai Pan Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex Frontiers in Neuroscience edge detection biological vision visual cortex self-attention mechanism convolutional neural network |
| title | Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| title_full | Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| title_fullStr | Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| title_full_unstemmed | Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| title_short | Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| title_sort | edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex |
| topic | edge detection biological vision visual cortex self-attention mechanism convolutional neural network |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.1073484/full |
| work_keys_str_mv | AT zhenguangzhang edgedetectionnetworksinspiredbyneuralmechanismsofselectiveattentioninbiologicalvisualcortex AT chuanlin edgedetectionnetworksinspiredbyneuralmechanismsofselectiveattentioninbiologicalvisualcortex AT yakunqiao edgedetectionnetworksinspiredbyneuralmechanismsofselectiveattentioninbiologicalvisualcortex AT yongcaipan edgedetectionnetworksinspiredbyneuralmechanismsofselectiveattentioninbiologicalvisualcortex |