Deep Transfer Learning for Biology Cross-Domain Image Classification
Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Journal of Control Science and Engineering |
| Online Access: | http://dx.doi.org/10.1155/2021/2518837 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546013987995648 |
|---|---|
| author | Chunfeng Guo Bin Wei Kun Yu |
| author_facet | Chunfeng Guo Bin Wei Kun Yu |
| author_sort | Chunfeng Guo |
| collection | DOAJ |
| description | Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning. |
| format | Article |
| id | doaj-art-bdd5e58e58e24d3cb16566608d9b7484 |
| institution | Kabale University |
| issn | 1687-5257 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Control Science and Engineering |
| spelling | doaj-art-bdd5e58e58e24d3cb16566608d9b74842025-02-03T07:24:09ZengWileyJournal of Control Science and Engineering1687-52572021-01-01202110.1155/2021/2518837Deep Transfer Learning for Biology Cross-Domain Image ClassificationChunfeng Guo0Bin Wei1Kun Yu2Shandong Foreign Trade Vocational CollegeThe Affiliated Hospital of Qingdao UniversityShandong Foreign Trade Vocational CollegeAutomatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning.http://dx.doi.org/10.1155/2021/2518837 |
| spellingShingle | Chunfeng Guo Bin Wei Kun Yu Deep Transfer Learning for Biology Cross-Domain Image Classification Journal of Control Science and Engineering |
| title | Deep Transfer Learning for Biology Cross-Domain Image Classification |
| title_full | Deep Transfer Learning for Biology Cross-Domain Image Classification |
| title_fullStr | Deep Transfer Learning for Biology Cross-Domain Image Classification |
| title_full_unstemmed | Deep Transfer Learning for Biology Cross-Domain Image Classification |
| title_short | Deep Transfer Learning for Biology Cross-Domain Image Classification |
| title_sort | deep transfer learning for biology cross domain image classification |
| url | http://dx.doi.org/10.1155/2021/2518837 |
| work_keys_str_mv | AT chunfengguo deeptransferlearningforbiologycrossdomainimageclassification AT binwei deeptransferlearningforbiologycrossdomainimageclassification AT kunyu deeptransferlearningforbiologycrossdomainimageclassification |