Next Article in Journal
Call Redistribution for a Call Center Based on Speech Emotion Recognition
Previous Article in Journal
Thermal Behavior of Single-Crystal Diamonds Catalyzed by Titanium Alloy at Elevated Temperature
Article

Weakly Supervised Fine-Grained Image Classification via Salient Region Localization and Different Layer Feature Fusion

1
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
2
School of Computers, Guangdong University of Technology, Guangzhou 510006, China
3
School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
4
Department of Computer and Information Science, University of Macau, Macau SAR 999078, China
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2020, 10(13), 4652; https://doi.org/10.3390/app10134652
Received: 19 June 2020 / Revised: 25 June 2020 / Accepted: 28 June 2020 / Published: 6 July 2020
(This article belongs to the Section Computing and Artificial Intelligence)
The fine-grained image classification task is about differentiating between different object classes. The difficulties of the task are large intra-class variance and small inter-class variance. For this reason, improving models’ accuracies on the task heavily relies on discriminative parts’ annotations and regional parts’ annotations. Such delicate annotations’ dependency causes the restriction on models’ practicability. To tackle this issue, a saliency module based on a weakly supervised fine-grained image classification model is proposed by this article. Through our salient region localization module, the proposed model can localize essential regional parts with the use of saliency maps, while only image class annotations are provided. Besides, the bilinear attention module can improve the performance on feature extraction by using higher- and lower-level layers of the network to fuse regional features with global features. With the application of the bilinear attention architecture, we propose the different layer feature fusion module to improve the expression ability of model features. We tested and verified our model on public datasets released specifically for fine-grained image classification. The results of our test show that our proposed model can achieve close to state-of-the-art classification performance on various datasets, while only the least training data are provided. Such a result indicates that the practicality of our model is incredibly improved since fine-grained image datasets are expensive. View Full-Text
Keywords: fine-grained image classification; different layer feature fusion; attention model fine-grained image classification; different layer feature fusion; attention model
Show Figures

Figure 1

MDPI and ACS Style

Chen, F.; Huang, G.; Lan, J.; Wu, Y.; Pun, C.-M.; Ling, W.-K.; Cheng, L. Weakly Supervised Fine-Grained Image Classification via Salient Region Localization and Different Layer Feature Fusion. Appl. Sci. 2020, 10, 4652. https://doi.org/10.3390/app10134652

AMA Style

Chen F, Huang G, Lan J, Wu Y, Pun C-M, Ling W-K, Cheng L. Weakly Supervised Fine-Grained Image Classification via Salient Region Localization and Different Layer Feature Fusion. Applied Sciences. 2020; 10(13):4652. https://doi.org/10.3390/app10134652

Chicago/Turabian Style

Chen, Fangxiong, Guoheng Huang, Jiaying Lan, Yanhui Wu, Chi-Man Pun, Wing-Kuen Ling, and Lianglun Cheng. 2020. "Weakly Supervised Fine-Grained Image Classification via Salient Region Localization and Different Layer Feature Fusion" Applied Sciences 10, no. 13: 4652. https://doi.org/10.3390/app10134652

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop