Semi-Supervised Learning via Clustering Representation Space
We proposed a novel loss function that combines supervised learning with clustering in deep neural networks. Taking advantage of the data distribution and the existence of some labeled data, we construct a meaningful latent space. Our loss function consists of three parts, the quality of the clustering result, the margin between clusters, and the classification error of labeled instances. Our proposed model is trained to minimize our loss function by backpropagation, avoiding the need for pre-training or additional networks. This guides our network to classify labeled samples correctly while able to find good clusters simultaneously. We applied our proposed method on MNIST, USPS, ETH-80, and COIL-100; the comparison results confirm our model's outstanding performance over semi-supervised learning.
PDF Abstract
USPS
