Adaptive Two-Dimensional Embedded Image Clustering


  • Zhihui Li University of New South Wales
  • Lina Yao University of New South Wales
  • Sen Wang University of Queensland
  • Salil Kanhere University of New South Wales
  • Xue Li University of Queensland
  • Huaxiang Zhang Shandong Normal University



With the rapid development of mobile devices, people are generating huge volumes of images data every day for sharing on social media, which draws much research attention to understanding the contents of images. Image clustering plays an important role in image understanding systems. Often, most of the existing image clustering algorithms flatten digital images that are originally represented by matrices into 1D vectors as the image representation for the subsequent learning. The drawbacks of vector-based algorithms include limited consideration of spatial relationship between pixels and computational complexity, both of which blame to the simple vectorized representation. To overcome the drawbacks, we propose a novel image clustering framework that can work directly on matrices of images instead of flattened vectors. Specifically, the proposed algorithm simultaneously learn the clustering results and preserve the original correlation information within the image matrix. To solve the challenging objective function, we propose a fast iterative solution. Extensive experiments have been conducted on various benchmark datasets. The experimental results confirm the superiority of the proposed algorithm.




How to Cite

Li, Z., Yao, L., Wang, S., Kanhere, S., Li, X., & Zhang, H. (2020). Adaptive Two-Dimensional Embedded Image Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4796-4803.



AAAI Technical Track: Machine Learning