BioEncoder : A metric learning toolkit for comparative organismal biology
(2024) In Ecology Letters 27(8).- Abstract
In the realm of biological image analysis, deep learning (DL) has become a core toolkit, for example for segmentation and classification. However, conventional DL methods are challenged by large biodiversity datasets characterized by unbalanced classes and hard-to-distinguish phenotypic differences between them. Here we present BioEncoder, a user-friendly toolkit for metric learning, which overcomes these challenges by focussing on learning relationships between individual data points rather than on the separability of classes. BioEncoder is released as a Python package, created for ease of use and flexibility across diverse datasets. It features taxon-agnostic data loaders, custom augmentation options, and simple hyperparameter... (More)
In the realm of biological image analysis, deep learning (DL) has become a core toolkit, for example for segmentation and classification. However, conventional DL methods are challenged by large biodiversity datasets characterized by unbalanced classes and hard-to-distinguish phenotypic differences between them. Here we present BioEncoder, a user-friendly toolkit for metric learning, which overcomes these challenges by focussing on learning relationships between individual data points rather than on the separability of classes. BioEncoder is released as a Python package, created for ease of use and flexibility across diverse datasets. It features taxon-agnostic data loaders, custom augmentation options, and simple hyperparameter adjustments through text-based configuration files. The toolkit's significance lies in its potential to unlock new research avenues in biological image analysis while democratizing access to advanced deep metric learning techniques. BioEncoder focuses on the urgent need for toolkits bridging the gap between complex DL pipelines and practical applications in biological research.
(Less)
- author
- Lürig, Moritz D LU ; Di Martino, Emanuela and Porto, Arthur
- organization
- publishing date
- 2024-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Deep Learning, Software, Animals, Image Processing, Computer-Assisted/methods, Biodiversity
- in
- Ecology Letters
- volume
- 27
- issue
- 8
- article number
- e14495
- publisher
- Wiley-Blackwell
- external identifiers
-
- scopus:85201098433
- pmid:39136114
- ISSN
- 1461-023X
- DOI
- 10.1111/ele.14495
- language
- English
- LU publication?
- yes
- additional info
- © 2024 The Author(s). Ecology Letters published by John Wiley & Sons Ltd.
- id
- 8fbbdeea-9919-4967-a905-e6582cad4006
- date added to LUP
- 2024-08-24 12:45:45
- date last changed
- 2024-09-08 05:13:51
@article{8fbbdeea-9919-4967-a905-e6582cad4006, abstract = {{<p>In the realm of biological image analysis, deep learning (DL) has become a core toolkit, for example for segmentation and classification. However, conventional DL methods are challenged by large biodiversity datasets characterized by unbalanced classes and hard-to-distinguish phenotypic differences between them. Here we present BioEncoder, a user-friendly toolkit for metric learning, which overcomes these challenges by focussing on learning relationships between individual data points rather than on the separability of classes. BioEncoder is released as a Python package, created for ease of use and flexibility across diverse datasets. It features taxon-agnostic data loaders, custom augmentation options, and simple hyperparameter adjustments through text-based configuration files. The toolkit's significance lies in its potential to unlock new research avenues in biological image analysis while democratizing access to advanced deep metric learning techniques. BioEncoder focuses on the urgent need for toolkits bridging the gap between complex DL pipelines and practical applications in biological research.</p>}}, author = {{Lürig, Moritz D and Di Martino, Emanuela and Porto, Arthur}}, issn = {{1461-023X}}, keywords = {{Deep Learning; Software; Animals; Image Processing, Computer-Assisted/methods; Biodiversity}}, language = {{eng}}, number = {{8}}, publisher = {{Wiley-Blackwell}}, series = {{Ecology Letters}}, title = {{BioEncoder : A metric learning toolkit for comparative organismal biology}}, url = {{http://dx.doi.org/10.1111/ele.14495}}, doi = {{10.1111/ele.14495}}, volume = {{27}}, year = {{2024}}, }