Name
Abstract | ||
|---|---|---|
Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph neural network with sparse structure to reduce redundant connectivity and learn compact representation. The network consists of 1) Seeding Module, which initializes the matching by generating a small set of reliable matches as seeds. 2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs. Three novel operations are proposed as basic elements for message passing: 1) Attentional Pooling, which aggregates keypoint features within the image to seed matches. 2) Seed Filtering, which enhances seed features and exchanges messages across images. 3) Attentional Unpooling, which propagates seed features back to original keypoints. Experiments show that our method reduces computational and memory complexity significantly compared with typical attention-based networks while competitive or higher performance is achieved. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICCV48922.2021.00624 | ICCV |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hongkai Chen | 1 | 0 | 1.35 |
| Zixin Luo | 2 | 32 | 4.43 |
| Jiahui Zhang | 3 | 16 | 2.21 |
| Lei Zhou | 4 | 3 | 2.39 |
| Bai Xuyang | 5 | 9 | 2.51 |
| Zeyu Hu | 6 | 0 | 1.35 |
| Chiew-Lan Tai | 7 | 1640 | 77.68 |
| Long Quan | 8 | 2436 | 169.17 |