Journal
PATTERN RECOGNITION
Volume 83, Issue -, Pages 161-173Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2018.05.019
Keywords
Image clustering; Fully convolutional auto-encoder; Representation learning; Discriminatively boosted clustering
Funding
- NNSF of China [91648205, 61627808, 61602483, 61603389]
Ask authors/readers for more resources
Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially. However, recent research results demonstrated that combining the separated phases in a unified framework and training them jointly can achieve a better performance. In this paper, we first introduce fully convolutional auto-encoders for image feature learning and then propose a unified clustering framework to learn image representations and cluster centers jointly based on a fully convolutional auto-encoder and soft k-means scores. At initial stages of the learning procedure, the representations extracted from the auto-encoder may not be very discriminative for latter clustering. We address this issue by adopting a boosted discriminative distribution, where high score assignments are highlighted and low score ones are de-emphasized. With the gradually boosted discrimination, clustering assignment scores are discriminated and cluster purities are enlarged. Experiments on several vision benchmark datasets show that our methods can achieve a state-of-the-art performance. (C) 2018 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available