Abstract
We present a image segmentation method based on deep hypercolumndescriptors which produces state-of-the-art results for thesegmentation of several classes of benign and malignant skin lesions.We achieve a Jaccard index of 0.792 on the 2017 ISIC SkinLesion Segmentation Challenge dataset.
Cite
CITATION STYLE
APA
Ramachandram, D., & Taylor, G. W. (2017). Skin Lesion Segmentation using Deep Hypercolumn Descriptors. Journal of Computational Vision and Imaging Systems, 3(1). https://doi.org/10.15353/vsnl.v3i1.173
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Already have an account? Sign in
Sign up for free