Bibliographic Details
| Title: |
A probabilistic constrained clustering for transfer learning and image category discovery |
| Authors: |
Hsu, Yen-Chang, Lv, Zhaoyang, Schlosser, Joel, Odom, Phillip, Kira, Zsolt |
| Publication Year: |
2018 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
| More Details: |
Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to formulate a clustering objective with pairwise constraints that can be used to train a deep clustering network; therefore the cluster assignments and their underlying feature representations are jointly optimized end-to-end. In this work, we provide a novel clustering formulation to address scalability issues of previous work in terms of optimizing deeper networks and larger amounts of categories. The proposed objective directly minimizes the negative log-likelihood of cluster assignment with respect to the pairwise constraints, has no hyper-parameters, and demonstrates improved scalability and performance on both supervised learning and unsupervised transfer learning.
Comment: CVPR 2018 Deep-Vision Workshop |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/1806.11078 |
| Accession Number: |
edsarx.1806.11078 |
| Database: |
arXiv |
