Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for 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.

Cite

Text

Xu et al. "Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for Image Retrieval." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12231

Markdown

[Xu et al. "Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for Image Retrieval." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/xu2018aaai-unsupervised/) doi:10.1609/AAAI.V32I1.12231

BibTeX

@inproceedings{xu2018aaai-unsupervised,
  title     = {{Unsupervised Part-Based Weighting Aggregation of Deep Convolutional Features for Image Retrieval}},
  author    = {Xu, Jian and Shi, Cunzhao and Qi, Cheng-Zuo and Wang, Chunheng and Xiao, Baihua},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {7436-7443},
  doi       = {10.1609/AAAI.V32I1.12231},
  url       = {https://mlanthology.org/aaai/2018/xu2018aaai-unsupervised/}
}