Deep Multi-label Classification in Affine Subspaces

Kurmann, Thomas; Márquez-Neila, Pablo; Wolf, Sebastian; Sznitman, Raphael (2019). Deep Multi-label Classification in Affine Subspaces. In: Shen, Dinggang; Liu, Tianming; Peters, Terry M.; Staib, Lawrence H.; Essert, Caroline; Zhou, Sean; Yap, Pew-Thian; Khan, Ali (eds.) MICCAI 2019. Lecture Notes in Computer Science: Vol. 11764 (pp. 165-173). Cham: Springer International Publishing 10.1007/978-3-030-32239-7_19

Text Kurmann2019_Chapter_DeepMulti-labelClassificationI.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (817kB)

Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation and yet provides more expressiveness than multi-class classification. However, to train MLCs, most methods have resorted to similar objective functions as with traditional multi-class classification settings. We show in this work that such approaches are not optimal and instead propose a novel deep MLC classification method in affine subspace. At its core, the method attempts to pull features of class-labels towards different affine subspaces while maximizing the distance between them. We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks. This method can be seen as a plug-in replacement loss function and is trainable in an end-to-end fashion.

Interest & Impact

Downloads

1 since deposited on 25 Oct 2019
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item