In: Medical Image Analysis 01 Pages 1-27 Elsevier 2022.
Abstract
Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task. However, we argue that such approaches are suboptimal because medical datasets are largely different from ImageNet and often contain limited training samples. In this work, we propose Task Agnostic Transfer Learning (TATL), a novel framework motivated by dermatologists' behaviors in the skincare context. TATL learns an attribute-agnostic segmenter that detects lesion skin regions and then transfers this knowledge to a set of attribute-specific classifiers to detect each particular attribute. Since TATL's attribute-agnostic segmenter only detects skin attribute regions, it enjoys ample data from all attributes, allows transferring knowledge among features, and compensates for the lack of training data from rare attributes. We conduct extensive experiments to evaluate the proposed TATL transfer learning mechanism with various neural network architectures on two popular skin attributes detection benchmarks. The empirical results show that TATL not only works well with multiple architectures but also can achieve state-of-the-art performances, while enjoying minimal model and computational complexities. We also provide theoretical insights and explanations for why our transfer learning framework performs well in practice.
@article{pub12216,
author = {
Nguyen, Ho Minh Duy
and
Nguyen, Thu T.
and
Vu, Huong
and
Pham, Quang
and
Nguyen, Manh-Duy
and
Nguyen, Binh T.
and
Sonntag, Daniel
},
title = {TATL: Task Agnostic Transfer Learning for Skin Attributes Detection},
year = {2022},
volume = {01},
pages = {1--27},
journal = {Medical Image Analysis},
publisher = {Elsevier}
}
German Research Center for Artificial Intelligence Deutsches Forschungszentrum für Künstliche Intelligenz
