We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Knowledge-Driven Network for Object Detection.
- Authors
Wu, Yundong; Liao, Jiajia; Liu, Yujun; Ding, Kaiming; Li, Shimin; Zhang, Zhilin; Cai, Guorong; Su, Jinhe
- Abstract
Object detection is a challenging computer vision task with numerous real-world applications. In recent years, the concept of the object relationship model has become helpful for object detection and has been verified and realized in deep learning. Nonetheless, most approaches to modeling object relations are limited to using the anchor-based algorithms; they cannot be directly migrated to the anchor-free frameworks. The reason is that the anchor-free algorithms are used to eliminate the complex design of anchors and predict heatmaps to represent the locations of keypoints of different object categories, without considering the relationship between keypoints. Therefore, to better fuse the information between the heatmap channels, it is important to model the visual relationship between keypoints. In this paper, we present a knowledge-driven network (KDNet)—a new architecture that can aggregate and model keypoint relations to augment object features for detection. Specifically, it processes a set of keypoints simultaneously through interactions between their local and geometric features, thereby allowing the modeling of their relationship. Finally, the updated heatmaps were used to obtain the corners of the objects and determine their positions. The experimental results conducted on the RIDER dataset confirm the effectiveness of the proposed KDNet, which significantly outperformed other state-of-the-art object detection methods.
- Subjects
DEEP learning; CONVOLUTIONAL neural networks
- Publication
Algorithms, 2021, Vol 14, Issue 7, p195
- ISSN
1999-4893
- Publication type
Article
- DOI
10.3390/a14070195