1. Squeezed Bilinear Pooling for Fine-Grained Visual Categorization
- Author
-
Qiyu Liao, Dadong Wang, Min Xu, and Hamish Holewa
- Subjects
Kernel (image processing) ,business.industry ,Computer science ,Pooling ,0202 electrical engineering, electronic engineering, information engineering ,Normalization (image processing) ,Bilinear interpolation ,020207 software engineering ,020201 artificial intelligence & image processing ,Pattern recognition ,02 engineering and technology ,Artificial intelligence ,business - 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.
- Published
- 2019