Title | ||
---|---|---|
Multilayer feature descriptors fusion CNN models for fine-grained visual recognition. |
Abstract | ||
---|---|---|
Fine-grained image classification is a challenging topic in the field of computer vision. General models based on first-order local features cannot achieve acceptable performance because the features are not so efficient in capturing fine-grained difference. A bilinear convolutional neural network (CNN) model exhibits that a second-order statistical feature is more efficient in capturing fine-grained difference than a first-order local feature. However, this framework only considers the extraction of a second-order feature descriptor, using a single convolutional layer. The potential effective classification features of other convolutional layers are ignored, resulting in loss of recognition accuracy. In this paper, a multilayer feature descriptors fusion CNN model is proposed. It fully considers the second-order feature descriptors and the first-order local feature descriptor generated by different layers. Experimental verification was carried out on fine-grained classification benchmark data sets, CUB-200-2011, Stanford Cars, and FGVC-aircraft. Compared with the bilinear CNN model, the proposed method has improved accuracy by 0.8%, 1.1%, and 5.5%. Compared with the compact bilinear pooling model, there is an accuracy increase of 0.64%, 1.63%, and 1.45%, respectively. In addition, the proposed model effectively uses multiple 1x1 convolution kernels to reduce dimension. The experimental results show that the multilayer low-dimensional second-order feature descriptors fusion model has comparable recognition accuracy of the original model. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1002/cav.1897 | COMPUTER ANIMATION AND VIRTUAL WORLDS |
Keywords | DocType | Volume |
convolutional neural network,deep learning,dimensionality reduction,fine-grained image classification,multilayer feature descriptors | Journal | 30.0 |
Issue | ISSN | Citations |
3-4 | 1546-4261 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong Hou | 1 | 33 | 3.88 |
Hangzai Luo | 2 | 718 | 43.92 |
Wanqing Zhao | 3 | 15 | 7.07 |
Xiang Zhang | 4 | 109 | 27.54 |
Jun Wang | 5 | 14 | 1.71 |
Jinye Peng | 6 | 284 | 40.93 |