Abstract
AbstractRecent studies have shown promising results on joint learning of local feature detectors and descriptors. To address the lack of ground-truth keypoint supervision, previous methods mainly inject appropriate knowledge about keypoint attributes into the network to facilitate model learning. In this paper, inspired by traditional corner detectors, we develop an end-to-end deep network, named Deep Corner, which adds a local similarity-based keypoint measure into a plain convolutional network. Deep Corner enables finding reliable keypoints and thus benefits the learning of the distinctive descriptors. Moreover, to improve keypoint localization, we first study previous multi-level keypoint detection strategies and then develop a multi-level U-Net architecture, where the similarity of features at multiple levels can be exploited effectively. Finally, to improve the invariance of descriptors, we propose a feature self-transformation operation, which transforms the learned features adaptively according to the specific local information. The experimental results on several tasks and comprehensive ablation studies demonstrate the effectiveness of our method and the involved components.
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software
Reference109 articles.
1. Arandjelović, R., & Zisserman, A. (2012). Three things everyone should know to improve object retrieval. In 2012 IEEE conference on computer vision and pattern recognition IEEE (pp. 2911–2918).
2. Balntas, V., Lenc, K., Vedaldi, A., & Mikolajczyk, K. (2017). Hpatches: A benchmark and evaluation of handcrafted and learned local descriptors. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5173–5182).
3. Balntas, V., Riba, E., Ponsa, D., & Mikolajczyk, K. (2016). Learning local feature descriptors with triplets and shallow convolutional neural networks. In Bmvc vol. 1 (p. 3).
4. Barroso-Laguna, A., Riba, E., Ponsa, D., & Mikolajczyk, K. (2019). Key.net: Keypoint detection by handcrafted and learned cnn filters. In Proceedings of the IEEE/CVF international conference on computer vision (ICCV)
5. Barroso-Laguna, A., Verdie, Y., Busam, B., & Mikolajczyk, K. (2020). Hdd-net: Hybrid detector descriptor with mutual interactive learning. In Proceedings of the Asian conference on computer vision.