Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis
© 2023. The Author(s)..
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:19 |
|---|---|
| Enthalten in: |
Plant methods - 19(2023), 1 vom: 13. Mai, Seite 46 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Yan, Jiawei [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Attention score |
|---|
| Anmerkungen: |
Date Revised 16.05.2023 published: Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1186/s13007-023-01020-2 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM356820807 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM356820807 | ||
| 003 | DE-627 | ||
| 005 | 20231226071257.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s13007-023-01020-2 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1189.xml |
| 035 | |a (DE-627)NLM356820807 | ||
| 035 | |a (NLM)37179312 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yan, Jiawei |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Improving multi-scale detection layers in the deep learning network for wheat spike detection based on interpretive analysis |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 16.05.2023 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2023. The Author(s). | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Attention score | |
| 650 | 4 | |a Deep learning network | |
| 650 | 4 | |a Interpretive analysis | |
| 650 | 4 | |a Wheat spike detection | |
| 700 | 1 | |a Zhao, Jianqing |e verfasserin |4 aut | |
| 700 | 1 | |a Cai, Yucheng |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Suwan |e verfasserin |4 aut | |
| 700 | 1 | |a Qiu, Xiaolei |e verfasserin |4 aut | |
| 700 | 1 | |a Yao, Xia |e verfasserin |4 aut | |
| 700 | 1 | |a Tian, Yongchao |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Yan |e verfasserin |4 aut | |
| 700 | 1 | |a Cao, Weixing |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Xiaohu |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Plant methods |d 2005 |g 19(2023), 1 vom: 13. Mai, Seite 46 |w (DE-627)NLM158775562 |x 1746-4811 |7 nnns |
| 773 | 1 | 8 | |g volume:19 |g year:2023 |g number:1 |g day:13 |g month:05 |g pages:46 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s13007-023-01020-2 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 19 |j 2023 |e 1 |b 13 |c 05 |h 46 | ||