Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2401.04984 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913191428096000 |
|---|---|
| author | Dai, Luanyuan Du, Xiaoyu Zhang, Hanwang Tang, Jinhui |
| author_facet | Dai, Luanyuan Du, Xiaoyu Zhang, Hanwang Tang, Jinhui |
| contents | Learning correspondences aims to find correct correspondences (inliers) from the initial correspondence set with an uneven correspondence distribution and a low inlier rate, which can be regarded as graph data. Recent advances usually use graph neural networks (GNNs) to build a single type of graph or simply stack local graphs into the global one to complete the task. But they ignore the complementary relationship between different types of graphs, which can effectively capture potential relationships among sparse correspondences. To address this problem, we propose MGNet to effectively combine multiple complementary graphs. To obtain information integrating implicit and explicit local graphs, we construct local graphs from implicit and explicit aspects and combine them effectively, which is used to build a global graph. Moreover, we propose Graph~Soft~Degree~Attention (GSDA) to make full use of all sparse correspondence information at once in the global graph, which can capture and amplify discriminative features. Extensive experiments demonstrate that MGNet outperforms state-of-the-art methods in different visual tasks. The code is provided in https://github.com/DAILUANYUAN/MGNet-2024AAAI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04984 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MGNet: Learning Correspondences via Multiple Graphs Dai, Luanyuan Du, Xiaoyu Zhang, Hanwang Tang, Jinhui Computer Vision and Pattern Recognition Learning correspondences aims to find correct correspondences (inliers) from the initial correspondence set with an uneven correspondence distribution and a low inlier rate, which can be regarded as graph data. Recent advances usually use graph neural networks (GNNs) to build a single type of graph or simply stack local graphs into the global one to complete the task. But they ignore the complementary relationship between different types of graphs, which can effectively capture potential relationships among sparse correspondences. To address this problem, we propose MGNet to effectively combine multiple complementary graphs. To obtain information integrating implicit and explicit local graphs, we construct local graphs from implicit and explicit aspects and combine them effectively, which is used to build a global graph. Moreover, we propose Graph~Soft~Degree~Attention (GSDA) to make full use of all sparse correspondence information at once in the global graph, which can capture and amplify discriminative features. Extensive experiments demonstrate that MGNet outperforms state-of-the-art methods in different visual tasks. The code is provided in https://github.com/DAILUANYUAN/MGNet-2024AAAI. |
| title | MGNet: Learning Correspondences via Multiple Graphs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.04984 |