Image Cosegmentation via Saliency-Guided Constrained Clustering with Cosine Similarity

Authors

  • Zhiqiang Tao Northeastern University
  • Hongfu Liu Northeastern University
  • Huazhu Fu <div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>Institute for Infocomm Research, Agency for Science, Technology and Research</span></p></div></div></div>
  • Yun Fu Northeastern University

Keywords:

Cosegmentation, Constrained Clustering, Saliency

Abstract

Cosegmentation jointly segments the common objects from multiple images. In this paper, a novel clustering algorithm, called Saliency-Guided Constrained Clustering approach with Cosine similarity (SGC3), is proposed for the image cosegmentation task, where the common foregrounds are extracted via a one-step clustering process. In our method, the unsupervised saliency prior is utilized as a partition-level side information to guide the clustering process. To guarantee the robustness to noise and outlier in the given prior, the similarities of instance-level and partition-level are jointly computed for cosegmentation. Specifically, we employ cosine distance to calculate the feature similarity between data point and its cluster centroid, and introduce a cosine utility function to measure the similarity between clustering result and the side information. These two parts are both based on the cosine similarity, which is able to capture the intrinsic structure of data, especially for the non-spherical cluster structure. Finally, a K-means-like optimization is designed to solve our objective function in an efficient way. Experimental results on two widely-used datasets demonstrate our approach achieves competitive performance over the state-of-the-art cosegmentation methods.

Downloads

Published

2017-02-12

How to Cite

Tao, Z., Liu, H., Fu, H., & Fu, Y. (2017). Image Cosegmentation via Saliency-Guided Constrained Clustering with Cosine Similarity. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11203