Mask-CNN: Localizing Parts and Selecting Descriptors
for Fine-Grained Bird Species Categorization
 |
Authors
Abstract
Fine-grained image recognition is a challenging computer vision problem, due to the small inter-class variations caused by highly similar subordinate categories, and the large intra-class variations in poses, scales and rotations. In this paper, we prove that selecting useful deep descriptors contributes well to fine-grained image recognition. Specifically, a novel Mask-CNN model without the fully connected layers is proposed. Based on the part annotations, the proposed model consists of a fully convolutional network to both locate the discriminative parts (e.g., head and torso), and more importantly generate weighted object/part masks for selecting useful and meaningful convolutional descriptors. After that, a three-stream Mask-CNN model is built for aggregating the selected object- and part-level descriptors simultaneously. Thanks to discarding the parameter redundant fully connected layers, our Mask-CNN has a small feature dimensionality and efficient inference speed by comparing with other fine-grained approaches. Furthermore, we obtain a new state-of-the-art accuracy on two challenging fine-grained bird species categorization datasets, which validates the effectiveness of both the descriptor selection scheme and the proposed Mask-CNN model.
Downloads
Code
 |
Datasets
 |
Related Papers
X.-S. Wei, C.-W. Xie, J. Wu, and C. Shen. Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Bird Species Categorization. Pattern Recognition, 2017, in press. DOI: 10.1016/j.patcog.2017.10.002.
X.-S. Wei, C.-W. Xie, and J. Wu. Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition. arXiv:1605.06878, 2016.