Quantifying plant mimesis in fossil insects using deep learning | |
Fan, Li2; Xu, Chunpeng(徐春鹏)1,3,4; Jarzembowski, Edmund A.1,4; Cui, Xiaohui2 | |
刊名 | HISTORICAL BIOLOGY |
2021-07-15 | |
页码 | 10 |
关键词 | Mimesis fossil insects similarity deep learning Siamese network |
ISSN号 | 0891-2963 |
DOI | 10.1080/08912963.2021.1952199 |
英文摘要 | As an important combination of behaviour and pattern in animals to resemble benign objects, biolog ical mimesis can effectively avoid the detection of their prey and predators. It at least dates back to the Permian in fossil records. The recognition of mimesis within fossil, however, might be subjective and lack quantitative analysis being only based on few fossils with limited information. To compensate for this omission, we propose a new method using a Siamese network to measure the dissimilarity between hypothetical mimics and their models from images. It generates dissimilarity values between paired images of organisms by extracting feature vectors and calculating Euclidean distances. Additionally, the idea of 'transfer learning' is adopted to fine-tune the Siamese network, to overcome the limitations of available fossil image pairs. We use the processed Totally-Looks-Like, a large similar image data set, to pretrain the Siamese network and fine-tune it with a collected mimetic-image data set. Based on our results, we propose two recommended image dissimilarity thresholds for judging the mimicry of extant insects (0-0.4556) and fossil insects (0-0.4717). Deep learning algorithms are used to quantify the mimicry of fossil insects in this study, providing novel insights into exploring the early evolution of mimicry. |
资助项目 | Strategic Priority Research Program of the Chinese Academy of Sciences[XDB26000000] ; Second Tibetan Plateau Scientific Expedition and Research[2019QZKK0706] ; National Natural Science Foundation of China[41688103] ; Chinese Academy of Sciences |
WOS关键词 | COLOR PATTERNS ; MIMICRY |
WOS研究方向 | Life Sciences & Biomedicine - Other Topics ; Paleontology |
语种 | 英语 |
出版者 | TAYLOR & FRANCIS LTD |
WOS记录号 | WOS:000673247500001 |
资助机构 | Strategic Priority Research Program of the Chinese Academy of Sciences ; Second Tibetan Plateau Scientific Expedition and Research ; National Natural Science Foundation of China ; Chinese Academy of Sciences |
内容类型 | 期刊论文 |
源URL | [http://ir.nigpas.ac.cn/handle/332004/38420] |
专题 | 中国科学院南京地质古生物研究所 |
通讯作者 | Cui, Xiaohui |
作者单位 | 1.Chinese Acad Sci, Nanjing Inst Geol & Palaeontol, State Key Lab Palaeobiol & Stratig, Nanjing, Peoples R China 2.Wuhan Univ, Sch Cyber Sci & Engn, Minist Educ, Key Lab Aerosp Informat Secur & Trusted Comp, Wuhan, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Ctr Excellence Life & Paleoenvironm, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Fan, Li,Xu, Chunpeng,Jarzembowski, Edmund A.,et al. Quantifying plant mimesis in fossil insects using deep learning[J]. HISTORICAL BIOLOGY,2021:10. |
APA | Fan, Li,Xu, Chunpeng,Jarzembowski, Edmund A.,&Cui, Xiaohui.(2021).Quantifying plant mimesis in fossil insects using deep learning.HISTORICAL BIOLOGY,10. |
MLA | Fan, Li,et al."Quantifying plant mimesis in fossil insects using deep learning".HISTORICAL BIOLOGY (2021):10. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论