A deep network loss for multi-label classification that learns class features in separate affine subspaces, reporting large gains over prior multi-label methods on two medical datasets.
In: Proceedings of the IEEE conference on computer vision and pattern recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Multi Label Classification in Affine Subspaces
A deep network loss for multi-label classification that learns class features in separate affine subspaces, reporting large gains over prior multi-label methods on two medical datasets.