Deep Discriminative Clustering Network
Lists
Only you see this
Abstract
Deep clustering aims to cluster unlabeled data by embedding them into a subspace based on deep model. The key challenge of deep clustering is to learn discriminative representations for input data with high dimensions. In this paper, we present a deep discriminative clustering network for clustering the real-world images. We use a convolutional auto-encoder stacked with a softmax layer to predict clustering assignments. To learn a discriminative representations, the proposed approach adds discriminative loss as embedded regularization with relative entropy minimization. With the discriminative loss, the network can not only produce clustering assignments, but also learn discriminative features by reducing intra-cluster distance and increasing inter-cluster distance. We evaluate the proposed method on three datasets: MNIST-full, YTF and FRGC-v2.0. We outperform state-of-the-art results on MNIST-full and FRGC-v2.0 and achieve competitive result on YTF. The source code has been made publicly available at https://github.com/shaoxuying/DeepDiscriminativeClusteringNetwork.
BibTeX
@inproceedings{shaol2018deep,
author = {Xuying Shaol and Ke-shi Ge and Huayou Su and Lei Luo and Baoyun Peng and Dongsheng Li},
title = {{Deep Discriminative Clustering Network}},
booktitle = {IJCNN},
year = {2018},
doi = {10.1109/ijcnn.2018.8489417},
}Loading related content...