Name
Abstract | ||
|---|---|---|
Fine-grained image classification is a challenging problem, due to the small inter-class variance caused by highly similar subordinate categories and large intra-class variance in poses, viewpoints and rotations. In this paper, we propose a novel end-to-end model for fine-grained image classification(FGIC). The proposed model consists of two sub-networks: detection sub-network and classification sub-network. The detection sub-network is constructed on the basis of R-FCN, and the classification sub-network contains a two-steam CNN for feature extraction and three fully connected layers for object classification. In addition, the network compression technology is adopted in both of the sub-networks to improve efficiency and reduce storage space. Experimental results on the CUB-200-2011 shows that the accuracy of our method is close to state-of-the-art with higher efficiency and lower storage requirement than the other compared methods (10 frames/sec during inference on TitanX). The proposed high-efficiency framework is believed to be effective in some of the practical applications, especially in the applications of mobile terminals. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/ISCID.2018.00015 | 2018 11th International Symposium on Computational Intelligence and Design (ISCID) |
Keywords | Field | DocType |
fine-grained classification,neural networks,object detection | Object detection,Pattern recognition,Viewpoints,Inference,Computer science,Feature extraction,Artificial intelligence,Contextual image classification,Artificial neural network | Conference |
Volume | ISSN | ISBN |
01 | 2165-1701 | 978-1-5386-8527-3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Ge | 1 | 2 | 4.09 |
| Xiaoguang Tu | 2 | 11 | 8.10 |
| Mei Xie | 3 | 56 | 13.64 |
| Zheng Ma | 4 | 376 | 46.43 |