Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for Image Retrieval

Authors

  • Jian Xu Institute of Automation, Chinese Academy of Sciences (CASIA); University of Chinese Academy of Sciences
  • Cunzhao Shi Institute of Automation, Chinese Academy of Sciences (CASIA)
  • Chengzuo Qi Institute of Automation, Chinese Academy of Sciences (CASIA); University of Chinese Academy of Sciences
  • Chunheng Wang Institute of Automation, Chinese Academy of Sciences (CASIA)
  • Baihua Xiao Institute of Automation, Chinese Academy of Sciences (CASIA)

Keywords:

Part-based weighting aggregation, Probabilistic proposals, Image retrieval

Abstract

In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the discriminative filters of deep convolutional layers as part detectors. Moreover, we propose the effective unsupervised strategy to select some part detectors to generate the "probabilistic proposals," which highlight certain discriminative parts of objects and suppress the noise of background. The final global PWA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. We conduct comprehensive experiments on four standard datasets and show that our unsupervised PWA outperforms the state-of-the-art unsupervised and supervised aggregation methods.

Downloads

Published

2018-04-27

How to Cite

Xu, J., Shi, C., Qi, C., Wang, C., & Xiao, B. (2018). Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12231