Multi-Scale Feature Fusion of Covariance Pooling Networks for Fine-Grained Visual Recognition
Author:
Qian Lulu1, Yu Tan2, Yang Jianyu1
Affiliation:
1. School of Rail Transportation, Soochow University, Suzhou 215131, China 2. ByteDance Inc., Moutainview, CA 94042, USA
Abstract
Multi-scale feature fusion techniques and covariance pooling have been shown to have positive implications for completing computer vision tasks, including fine-grained image classification. However, existing algorithms that use multi-scale feature fusion techniques for fine-grained classification tend to consider only the first-order information of the features, failing to capture more discriminative features. Likewise, existing fine-grained classification algorithms using covariance pooling tend to focus only on the correlation between feature channels without considering how to better capture the global and local features of the image. Therefore, this paper proposes a multi-scale covariance pooling network (MSCPN) that can capture and better fuse features at different scales to generate more representative features. Experimental results on the CUB200 and MIT indoor67 datasets achieve state-of-the-art performance (CUB200: 94.31% and MIT indoor67: 92.11%).
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference59 articles.
1. Yang, J., Duan, J., Li, T., Hu, C., Liang, J., and Shi, T. (2022). Tool Wear Monitoring in Milling Based on Fine-Grained Image Classification of Machined Surface Images. Sensors, 22. 2. Zhou, X., Zhang, Y., and Wei, Q. (2022). Few-Shot Fine-Grained Image Classification via GNN. Sensors, 22. 3. Wang, Y., Mamat, H., Xu, X., Aysa, A., and Ubul, K. (2022). Scene Uyghur Text Detection Based on Fine-Grained Feature Representation. Sensors, 22. 4. Karlinsky, L., Shtok, J., Tzur, Y., and Tzadok, A. (2017, January 21–26). Fine-grained recognition of thousands of object categories with single-example training. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 5. Herranz, L., Jiang, S., and Li, X. (July, January 26). Scene recognition with CNNs: Objects, scales and dataset bias. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|