Cargando…
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...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044259/ https://www.ncbi.nlm.nih.gov/pubmed/35494849 http://dx.doi.org/10.7717/peerj-cs.931 |
_version_ | 1784695066989690880 |
---|---|
author | Dong, Yan Liu, Yundong Kang, Haonan Li, Chunlei Liu, Pengcheng Liu, Zhoufeng |
author_facet | Dong, Yan Liu, Yundong Kang, Haonan Li, Chunlei Liu, Pengcheng Liu, Zhoufeng |
author_sort | Dong, Yan |
collection | PubMed |
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. |
format | Online Article Text |
id | pubmed-9044259 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-90442592022-04-28 Lightweight and efficient neural network with SPSA attention for wheat ear detection Dong, Yan Liu, Yundong Kang, Haonan Li, Chunlei Liu, Pengcheng Liu, Zhoufeng PeerJ Comput Sci Artificial Intelligence 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. PeerJ Inc. 2022-04-05 /pmc/articles/PMC9044259/ /pubmed/35494849 http://dx.doi.org/10.7717/peerj-cs.931 Text en © 2022 Dong et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited. |
spellingShingle | Artificial Intelligence Dong, Yan Liu, Yundong Kang, Haonan Li, Chunlei Liu, Pengcheng Liu, Zhoufeng Lightweight and efficient neural network with SPSA attention for wheat ear detection |
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 | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044259/ https://www.ncbi.nlm.nih.gov/pubmed/35494849 http://dx.doi.org/10.7717/peerj-cs.931 |
work_keys_str_mv | AT dongyan lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT liuyundong lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT kanghaonan lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT lichunlei lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT liupengcheng lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection AT liuzhoufeng lightweightandefficientneuralnetworkwithspsaattentionforwheateardetection |