Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning. Bilinear pooling based models have been shown to be effective at fine-grained recognition, while most previous approaches neglect the fact that inter-layer part feature interaction and fine-grained feature learning are mutually correlated and can reinforce each other. In this paper, we present a novel model to address these issues. First, a cross-layer bilinear pooling approach is proposed to capture the inter-layer part feature relations, which results in superior performance compared with other bilinear pooling based approaches. Second, we propose a novel hierarchical bilinear pooling framework to integrate multiple cross-layer bilinear features to enhance their representation capability. Our formulation is intuitive, efficient and achieves state-of-the-art results on the widely used fine-grained recognition datasets.
@article{arxiv.1807.09915,
title = {Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition},
author = {Chaojian Yu and Xinyi Zhao and Qi Zheng and Peng Zhang and Xinge You},
journal= {arXiv preprint arXiv:1807.09915},
year = {2018}
}