P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization

Junwei Han, Xiwen Yao, Gong Cheng, Xiaoxu Feng, Dong Xu

Abstract

This paper proposes an end-to-end fine-grained visual categorization system, termed Part-based Convolutional Neural Network (P-CNN), which consists of three modules. The first module is a Squeeze-and-Excitation (SE) block, which learns to recalibrate channel-wise feature responses by emphasizing informative channels and suppressing less useful ones. The second module is a Part Localization Network (PLN) used to locate distinctive object parts, through which a bank of convolutional filters are learned as discriminative part detectors. Thus, a group of informative parts can be discovered by convolving the feature maps with each part detector. The third module is a Part Classification Network (PCN) that has two streams. The first stream classifies each individual object part into image-level categories. The second stream concatenates part features and global feature into a joint feature for the final classification. In order to learn powerful part features and boost the joint feature capability, we propose a Duplex Focal Loss used for metric learning and part classification, which focuses on training hard examples. We further merge PLN and PCN into a unified network for an end-to-end training process via a simple training technique. Comprehensive experiments and comparisons with state-of-the-art methods on three benchmark datasets demonstrate the effectiveness of our proposed method.
BibTeX
@article{han2022p,
  author = {Junwei Han and Xiwen Yao and Gong Cheng and Xiaoxu Feng and Dong Xu},
  title = {{P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2022},
  url = {https://openreview.net/forum?id=zjrygzJZIG},
}

Loading related content...

Figure