Averse Deep Semantic Segmentation

• Type: Article in International Conference Proceedings Book
• Date: 2019

Authors

Ricardo Cruz (Author) Other; Joaquim F. Pinto Costa (Author) FCUP; Jaime S. Cardoso (Author) FEUP

Conference proceedings International

Title: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

Pages: 44-47

41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

23 July 2019 through 27 July 2019

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 1 Citation

Other information

Authenticus ID: P-00R-8JP

DOI: 10.1109/embc.2019.8857385

Abstract (EN): Semantic segmentation consists in predicting whether any given pixel is part of the object of interest or not. Two types of errors are therefore possible: false positives and false negatives. For visualization and emphasis purposes, we might want to put special effort into reducing one type of error in detriment of the other. A common practice is to define the two types of errors as a relative trade-off using a cost matrix. However, it might be more natural for humans to define the trade-off in terms of an absolute constraint on one type of errors while trying to minimize the other. Previously, we suggested possible approaches to introduce this absolute trade-off in binary classifiers. Extending to semantic segmentation, we propose a threshold on the sigmoid layer and modifications to gradient descent such as adding a new term to the loss function and training in two phases. The latter produced the more resilient results, with a simple threshold being sufficient in most cases.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 4