.png){kind=icon}
返回
Deep Corner
.png){kind=icon}
OA
AI
DOI：10.1007/s11263-023-01837-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent 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.
Keyword:
Detector
Descriptor
Local feature
Keypoint
Image matching
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
Orbital-angular-momentum-multiplexed free-space optical communication link using transmitter lenses
OAAI
OAAI分享收藏分享收藏Different Forms of Vigilance in Response to the Presence of Predators and Conspecifics in a Group‐Living Mammal, the European Rabbit.png)
Ethology
EthologyIF0
PREAI
分享收藏分享收藏AutoMorph: Automated Retinal Vascular Morphology Quantification Via a Deep Learning PipelineAutoMorph: 通过深度学习管道自动量化视网膜血管形态OAAI
OAAI分享收藏
查看更多内容