Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis
Abstract Background Detecting and counting wheat spikes is essential for predicting and measuring wheat yield. However, current wheat spike detection researches often directly apply the new network structure. There are few studies that can combine the prior knowledge of wheat spike size characterist...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-023-01020-2 |
| _version_ | 1797827536279830528 |
|---|---|
| author | Jiawei Yan Jianqing Zhao Yucheng Cai Suwan Wang Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao Xiaohu Zhang |
| author_facet | Jiawei Yan Jianqing Zhao Yucheng Cai Suwan Wang Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao Xiaohu Zhang |
| author_sort | Jiawei Yan |
| collection | DOAJ |
| description | Abstract Background Detecting and counting wheat spikes is essential for predicting and measuring wheat yield. However, current wheat spike detection researches often directly apply the new network structure. There are few studies that can combine the prior knowledge of wheat spike size characteristics to design a suitable wheat spike detection model. It remains unclear whether the complex detection layers of the network play their intended role. Results This study proposes an interpretive analysis method for quantitatively evaluating the role of three-scale detection layers in a deep learning-based wheat spike detection model. The attention scores in each detection layer of the YOLOv5 network are calculated using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm, which compares the prior labeled wheat spike bounding boxes with the attention areas of the network. By refining the multi-scale detection layers using the attention scores, a better wheat spike detection network is obtained. The experiments on the Global Wheat Head Detection (GWHD) dataset show that the large-scale detection layer performs poorly, while the medium-scale detection layer performs best among the three-scale detection layers. Consequently, the large-scale detection layer is removed, a micro-scale detection layer is added, and the feature extraction ability in the medium-scale detection layer is enhanced. The refined model increases the detection accuracy and reduces the network complexity by decreasing the network parameters. Conclusion The proposed interpretive analysis method to evaluate the contribution of different detection layers in the wheat spike detection network and provide a correct network improvement scheme. The findings of this study will offer a useful reference for future applications of deep network refinement in this field. |
| first_indexed | 2024-04-09T12:49:53Z |
| format | Article |
| id | doaj.art-d33294198d7a43cba4a3bfecdf6141c3 |
| institution | Directory Open Access Journal |
| issn | 1746-4811 |
| language | English |
| last_indexed | 2024-04-09T12:49:53Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj.art-d33294198d7a43cba4a3bfecdf6141c32023-05-14T11:18:07ZengBMCPlant Methods1746-48112023-05-0119111310.1186/s13007-023-01020-2Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysisJiawei Yan0Jianqing Zhao1Yucheng Cai2Suwan Wang3Xiaolei Qiu4Xia Yao5Yongchao Tian6Yan Zhu7Weixing Cao8Xiaohu Zhang9National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural UniversityAbstract Background Detecting and counting wheat spikes is essential for predicting and measuring wheat yield. However, current wheat spike detection researches often directly apply the new network structure. There are few studies that can combine the prior knowledge of wheat spike size characteristics to design a suitable wheat spike detection model. It remains unclear whether the complex detection layers of the network play their intended role. Results This study proposes an interpretive analysis method for quantitatively evaluating the role of three-scale detection layers in a deep learning-based wheat spike detection model. The attention scores in each detection layer of the YOLOv5 network are calculated using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm, which compares the prior labeled wheat spike bounding boxes with the attention areas of the network. By refining the multi-scale detection layers using the attention scores, a better wheat spike detection network is obtained. The experiments on the Global Wheat Head Detection (GWHD) dataset show that the large-scale detection layer performs poorly, while the medium-scale detection layer performs best among the three-scale detection layers. Consequently, the large-scale detection layer is removed, a micro-scale detection layer is added, and the feature extraction ability in the medium-scale detection layer is enhanced. The refined model increases the detection accuracy and reduces the network complexity by decreasing the network parameters. Conclusion The proposed interpretive analysis method to evaluate the contribution of different detection layers in the wheat spike detection network and provide a correct network improvement scheme. The findings of this study will offer a useful reference for future applications of deep network refinement in this field.https://doi.org/10.1186/s13007-023-01020-2Wheat spike detectionDeep learning networkAttention scoreInterpretive analysis |
| spellingShingle | Jiawei Yan Jianqing Zhao Yucheng Cai Suwan Wang Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao Xiaohu Zhang Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis Plant Methods Wheat spike detection Deep learning network Attention score Interpretive analysis |
| title | Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| title_full | Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| title_fullStr | Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| title_full_unstemmed | Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| title_short | Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| title_sort | improving multi scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| topic | Wheat spike detection Deep learning network Attention score Interpretive analysis |
| url | https://doi.org/10.1186/s13007-023-01020-2 |
| work_keys_str_mv | AT jiaweiyan improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT jianqingzhao improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT yuchengcai improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT suwanwang improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT xiaoleiqiu improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT xiayao improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT yongchaotian improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT yanzhu improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT weixingcao improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis AT xiaohuzhang improvingmultiscaledetectionlayersinthedeeplearningnetworkforwheatspikedetectionbasedoninterpretiveanalysis |