Squeezed Bilinear Pooling for Fine-Grained Visual Categorization

Qiyu Liao, Dadong Wang, Hamish Holewa, Min Xu

ICCVW 2019 pp. 728-732

doi:10.1109/ICCVW.2019.00093 /iccvw/2019/liao2019iccvw-squeezed/

Abstract

In this paper, we propose a supervised selection based method to decrease both the computation and the feature dimension of the original bilinear pooling. Different from currently existing compressed second-order pooling methods, the proposed selection method is matrix normalization applicable. Moreover, by extracting the selected highly semantic feature channels, we proposed the Fisher- Recurrent-Attention structure and achieved state-of-the-art fine-grained classification results among the VGG-16 based models.

ICCVW Semantic Scholar

Cite

Text

Liao et al. "Squeezed Bilinear Pooling for Fine-Grained Visual Categorization." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00093

Markdown

[Liao et al. "Squeezed Bilinear Pooling for Fine-Grained Visual Categorization." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/liao2019iccvw-squeezed/) doi:10.1109/ICCVW.2019.00093

BibTeX

@inproceedings{liao2019iccvw-squeezed,
  title     = {{Squeezed Bilinear Pooling for Fine-Grained Visual Categorization}},
  author    = {Liao, Qiyu and Wang, Dadong and Holewa, Hamish and Xu, Min},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {728-732},
  doi       = {10.1109/ICCVW.2019.00093},
  url       = {https://mlanthology.org/iccvw/2019/liao2019iccvw-squeezed/}
}