A probabilistic constrained clustering for transfer learning and image category discovery
arXiv:1806.11078
Abstract
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.
arXiv commentCVPR 2018 Deep-Vision Workshop
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- On Constrained Spectral Clustering and Its Applications
- Learning to cluster in order to transfer across domains and tasks
- Neural network-based clustering using pairwise constraints
- Deep Image Category Discovery using a Transferred Similarity Function
- Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video
- Semi-supervised Kernel Metric Learning Using Relative Comparisons