1. AFSRNet: learning local descriptors with adaptive multi-scale feature fusion and symmetric regularization.
- Author
-
Li, Dong, Liang, Haowen, and Lam, Kin-Man
- Subjects
CONVOLUTIONAL neural networks ,COMPUTER performance ,DESCRIPTOR systems ,DEEP learning - Abstract
Multi-scale feature fusion has been widely used in handcrafted descriptors, but has not been fully explored in deep learning-based descriptor extraction. Simple concatenation of descriptors of different scales has not been successful in significantly improving performance for computer vision tasks. In this paper, we propose a novel convolutional neural network, based on center-surround adaptive multi-scale feature fusion. Our approach enables the network to focus on different center-surround scales, resulting in improved performance. We also introduce a novel regularization technique that uses second-order similarity to constrain the learning of local descriptors, based on the symmetric property of the similarity matrix. The proposed method outperforms single-scale or simple-concatenation descriptors on two datasets and achieves state-of-the-art results on the Brown dataset. Furthermore, our method demonstrates excellent generalization ability on the HPatches dataset. Our code is released on GitHub: https://github.com/Leung-GD/AFSRNet/tree/main. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF