Lightweight and efficient neural network with SPSA attention for wheat ear detection
Advancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-04-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-931.pdf |
| _version_ | 1818393923525017600 |
|---|---|
| author | Yan Dong Yundong Liu Haonan Kang Chunlei Li Pengcheng Liu Zhoufeng Liu |
| author_facet | Yan Dong Yundong Liu Haonan Kang Chunlei Li Pengcheng Liu Zhoufeng Liu |
| author_sort | Yan Dong |
| collection | DOAJ |
| description | Advancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress in improving detection accuracy. However, some of them are not able to make a good balance between computational cost and precision to meet the needs of deployment in real world. To address these issues, a lightweight and efficient wheat ear detector with Shuffle Polarized Self-Attention (SPSA) is proposed in this paper. Specifically, we first utilize a lightweight backbone network with asymmetric convolution for effective feature extraction. Next, SPSA attention is given to adaptively select focused positions and produce a more discriminative representation of the features. This strategy introduces polarized self-attention to spatial dimension and channel dimension and adopts Shuffle Units to combine those two types of attention mechanisms effectively. Finally, the TanhExp activation function is adopted to accelerate the inference speed and reduce the training time, and CIOU loss is used as the border regression loss function to enhance the detection ability of occlusion and overlaps between targets. Experimental results on the Global Wheat Head Detection dataset show that our method achieves superior detection performance compared with other state-of-the-art approaches. |
| first_indexed | 2024-12-14T05:53:01Z |
| format | Article |
| id | doaj.art-d00bd000e15f4ec8b45f380ae4e0aec1 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-14T05:53:01Z |
| publishDate | 2022-04-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-d00bd000e15f4ec8b45f380ae4e0aec12022-12-21T23:14:40ZengPeerJ Inc.PeerJ Computer Science2376-59922022-04-018e93110.7717/peerj-cs.931Lightweight and efficient neural network with SPSA attention for wheat ear detectionYan Dong0Yundong Liu1Haonan Kang2Chunlei Li3Pengcheng Liu4Zhoufeng Liu5School of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, ChinaSchool of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, ChinaDepartment of Statistics and Data Science, National University of Singapore, SingaporeSchool of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, ChinaDepartment of Computer Science, University of York, York, United KingdomSchool of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, ChinaAdvancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress in improving detection accuracy. However, some of them are not able to make a good balance between computational cost and precision to meet the needs of deployment in real world. To address these issues, a lightweight and efficient wheat ear detector with Shuffle Polarized Self-Attention (SPSA) is proposed in this paper. Specifically, we first utilize a lightweight backbone network with asymmetric convolution for effective feature extraction. Next, SPSA attention is given to adaptively select focused positions and produce a more discriminative representation of the features. This strategy introduces polarized self-attention to spatial dimension and channel dimension and adopts Shuffle Units to combine those two types of attention mechanisms effectively. Finally, the TanhExp activation function is adopted to accelerate the inference speed and reduce the training time, and CIOU loss is used as the border regression loss function to enhance the detection ability of occlusion and overlaps between targets. Experimental results on the Global Wheat Head Detection dataset show that our method achieves superior detection performance compared with other state-of-the-art approaches.https://peerj.com/articles/cs-931.pdfWheat earsDeep neural networksLightweightPolarized self-attention |
| spellingShingle | Yan Dong Yundong Liu Haonan Kang Chunlei Li Pengcheng Liu Zhoufeng Liu Lightweight and efficient neural network with SPSA attention for wheat ear detection PeerJ Computer Science Wheat ears Deep neural networks Lightweight Polarized self-attention |
| title | Lightweight and efficient neural network with SPSA attention for wheat ear detection |
| title_full | Lightweight and efficient neural network with SPSA attention for wheat ear detection |
| title_fullStr | Lightweight and efficient neural network with SPSA attention for wheat ear detection |
| title_full_unstemmed | Lightweight and efficient neural network with SPSA attention for wheat ear detection |
| title_short | Lightweight and efficient neural network with SPSA attention for wheat ear detection |
| title_sort | lightweight and efficient neural network with spsa attention for wheat ear detection |
| topic | Wheat ears Deep neural networks Lightweight Polarized self-attention |
| url | https://peerj.com/articles/cs-931.pdf |
| work_keys_str_mv | AT yandong lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT yundongliu lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT haonankang lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT chunleili lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT pengchengliu lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT zhoufengliu lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection |