Abstract
Cyber-Physical-Social Systems (CPSS) integrates cyber, physical and social spaces together, which makes our lives more convenient and intelligent by providing personalized service. In this paper, we will provide CPSS service for fine-grained recognition. Fine-grained visual recognition is a hot but challenging research in computer vision that aims to recognize object subcategories. The reason why it is challenging is that it extremely depends on the subtle discriminative features of local parts. Recently, some bilinear feature based methods were proposed, and the experimental results show state-of-the-art performance. However, most of them neglect the spatial relationships of part-region feature among multiple layers. In this paper, a novel approach of Self-layer and Cross-layer Bilinear Aggregation(SCBA) is proposed for fine-grained recognition. Firstly, a self-layer bilinear feature fusion module is proposed to model the spatial relationship of feature at the same layer. Secondly, we propose a cross-layer bilinear feature fusion module to capture the inter-layer interreaction of information to boost the ability of feature representation. In summary, the method we proposed not only can learn the correlations among different layers but the same layer, which makes it efficient and the experimental results show that it achieves state-of-the-art accuracy on three common fine-grained image datasets.
Highlights
With the deepening of application of network, especially, the internet plus, big data, cloud computing, internet of things, information and physical systems are further integrated, the network and human society are seamlessly integrated, forming a more complex system that integrates Human, machine and information
We propose Self-layer and Cross-layer Bilinear Aggregation (SCBA) model to strengthen the representation ability of bilinear features
PROPOSED APPROACH we develop a self-layer and cross-layer bilinear aggregation(SCBA) model to overcome those limitations mentioned above
Summary
With the deepening of application of network, especially, the internet plus, big data, cloud computing, internet of things, information and physical systems are further integrated, the network and human society are seamlessly integrated, forming a more complex system that integrates Human, machine and information. Because of those uncertainties, including occlusion, illumination, pose, complex background, and etc, leading to large variance of the same subcategory and high similarity of different subcategory in fine-grained images (see Figure 1). Overlook the relationships among different layers that can strengthen the ability of feature representation Considering these limitations mentioned above, some methods [15]–[17] propose bilinear pooling to obtain more powerful feature representations. We exploit a plain but valid self-layer and cross-layer bilinear feature representation method that simultaneously obtains the self-channel relationships in single layer and inter-layer interaction of features among multiple layers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
