Less Is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation
Abstract
Segmenting skin lesions images is relevant both for itself and for assisting in lesion classification, but suffers from the challenge in obtaining annotated data. In this work, we show that segmentation may improve with less data, by selecting the training samples with best inter-annotator agreement, and conditioning the ground-truth masks to remove excessive detail. We perform an exhaustive experimental design considering several sources of variation, including three different test sets, two different deep-learning architectures, and several replications, for a total of 540 experimental runs. We found that sample selection and detail removal may have impacts corresponding, respectively, to 12% and 16% of the one obtained by picking a better deep-learning model.
Cite
Text
Ribeiro et al. "Less Is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00377Markdown
[Ribeiro et al. "Less Is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/ribeiro2020cvprw-less/) doi:10.1109/CVPRW50498.2020.00377BibTeX
@inproceedings{ribeiro2020cvprw-less,
title = {{Less Is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation}},
author = {Ribeiro, Vinícius and Avila, Sandra and Valle, Eduardo},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {3182-3191},
doi = {10.1109/CVPRW50498.2020.00377},
url = {https://mlanthology.org/cvprw/2020/ribeiro2020cvprw-less/}
}