Multi-feature fusion of convolutional neural networks for Fine-Grained ship classification

Issue title: Special Section: Intelligent Data Aggregation Inspired Paradigm and Approaches in IoT Applications

Guest editors: Xiaohui Yuan and Mohamed Elhoseny

Article type: Research Article

Authors: Huang, Sizhe^{a; b; *} | Xu, Huosheng^b | Xia, Xuezhi^b | Yang, Fan^c | Zou, Fuhao^c

Affiliations: [a] College of Computer Science and Technology, Harbin Engineering University, Harbin, China | [b] Wuhan Digital Engineering Research Institute, Wuhan, China | [c] College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China

Correspondence: [*] Corresponding author. Sizhe Huang. E-mail: [email protected].

Abstract:  Fine-Grained ship classification is quite challenging because the visual differences between the subcategories are small. Due to the large intra-class similarity, it is very difficult to classify the ship objects without bounding box/part annotations. In this paper, we propose a model that combines multiple deep CNN features and use fusion strategies to explore of multi-scale features relationship. Because different levels/depths CNN features have different properties, so we combine multiple low-level local CNN features with high-level global CNN feature for object classification. The model shows a good way of tailoring pre-trained CNN models to fine-grained ship classification, which have lower cost in computation and storage compared with some state-of-the-art CNN methods and achieves the significant classification performances in FGVC-Aircraft and Stanford Cars datasets.

Keywords: Convolutional neural networks, Fine-grained classification, ship recognition

DOI: 10.3233/JIFS-179071

Journal: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 1, pp. 125-135, 2019