200 citations · 207 across the 2 of their papers we have counts for
2 papers
cs.LG2017★ 7 cited
Between-class Learning for Image Classification
Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada
In this paper, we propose a novel learning method for image classification called Between-Class learning (BC learning). We generate between-class images by mixing two images belong…
cs.LG2017★ 200 cited
Learning from Between-class Examples for Deep Sound Recognition
Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada
Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose…