Loading [a11y]/accessibility-menu.js
How Do Different Tasks Influence Each Other’s Learning? Case Study In Dermoscopic Images | IEEE Conference Publication | IEEE Xplore
Scheduled Maintenance: On Monday, 27 January, the IEEE Xplore Author Profile management portal will undergo scheduled maintenance from 9:00-11:00 AM ET (1400-1600 UTC). During this time, access to the portal will be unavailable. We apologize for any inconvenience.

How Do Different Tasks Influence Each Other’s Learning? Case Study In Dermoscopic Images


Abstract:

Multitask learning is arousing great interest for its ability to regularize models, or improve the generalization ability of the tasks that are learned simultaneously. In...Show More

Abstract:

Multitask learning is arousing great interest for its ability to regularize models, or improve the generalization ability of the tasks that are learned simultaneously. In this work, we present a model based on Convolutional Neural Networks that uses a multitask learning approach to simultaneously segment the skin lesion, segment the hairs of the lesion and perform the inpainting of these hairs. In addition, we study how different combinations of these tasks influence each other. The experiments are carried out on images from five publicly available datasets such as PH2, dermquest, dermis, EDRA2002 and the ISIC Data Archive. We ascertain that optimizing a combined loss function while sharing hidden representations among the related tasks, may improve the ability to generalize when compared to each of the single-task contributions.
Date of Conference: 13-16 April 2021
Date Added to IEEE Xplore: 25 May 2021
ISBN Information:

ISSN Information:

Conference Location: Nice, France

References

References is not available for this document.