Share Email Print
cover

Proceedings Paper • new

MBNet: multi-scale bilinear convolutional neural networks for fine-grained visual classification towards real-time tasks
Author(s): Tingqiang Deng; Rui Li; Chunguo Li; Rutian Liao; Yang Liu; Zhe Yang; Luxi Yang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Fine-grained visual classification (FGVC) is difficult due to the under-utilization of low-level features. This paper proposes a real-time method MBNet based on multi-stream multi-scale cross bilinear CNN that contributes to solving the problem. First, each layer of the multi-stream CNN is extracted by basic network such as VGGNet and others, followed by calculating multi-stream cross bilinear vector and bottom bilinear vector of low and high level features respectively. The FGVC results are predicted after feature fusion, which solves the problem that small and low-level details in the original image are easily overlooked. In the widely used datasets Caltech-UCSD Birds, Stanford Cars and Aircraft, the proposed method shows that the accuracy is significantly improved compared to the existing methods, reaching to state of the art level of 88.51%, 94.73% and 92.41%. It also meets the requirements of real-time tasks.

Paper Details

Date Published: 31 July 2019
PDF: 6 pages
Proc. SPIE 11198, Fourth International Workshop on Pattern Recognition, 1119806 (31 July 2019); doi: 10.1117/12.2540365
Show Author Affiliations
Tingqiang Deng, Southeast Univ. (China)
Rui Li, Southeast Univ. (China)
Chunguo Li, Southeast Univ. (China)
Rutian Liao, Southeast Univ. (China)
Yang Liu, Southeast Univ. (China)
Zhe Yang, Southeast Univ. (China)
Luxi Yang, Southeast Univ. (China)


Published in SPIE Proceedings Vol. 11198:
Fourth International Workshop on Pattern Recognition
Xudong Jiang; Zhenxiang Chen; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top