Tomohiko Konno, Michiaki Iwazume
We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.
Tomohiko Konno, Michiaki Iwazume
Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity filling, improves the deep learning capabilities in several problems because all the real-world data are observed to be imbalanced.