2015/11/19 by Sheng-Yi Bai, Bai, Sheng-Yi, Sebastian Agethen +5
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.1511.06104
As the original submission of iclr is withdrawn, the arxiv submission should be withdrawn as well
arxiv created 2016/01/19 · arxiv updated 2016/01/20
The recent promising achievements of deep learning rely on the large amount of labeled data. Considering the abundance of data on the web, most of them do not have labels at all. Therefore, it is important to improve generalization performance using unlabeled data on supervised tasks with few labeled instances. In this work, we revisit graph-based semi-supervised learning algorithms and propose an online graph construction technique which suits deep convolutional neural network better. We consider an EM-like algorithm for semi-supervised learning on deep neural networks: In forward pass, the graph is constructed based on the network output, and the graph is then used for loss calculation to help update the network by back propagation in the backward pass. We demonstrate the strength of our online approach compared to the conventional ones whose graph is constructed on static but not robust enough feature representations beforehand.