Back to Search
Start Over
DFR-net: Learning Dense Features at the Resolution Level
- Source :
- IEEE Access, Vol 7, Pp 97013-97020 (2019)
- Publication Year :
- 2019
- Publisher :
- IEEE, 2019.
-
Abstract
- Patch matching is a significant stage in numerous computer vision tasks. This paper proposed a novel network structure, named DFR-net, appropriate to match patches. The proposed network uses a dense connectivity pattern at the resolution level, making the training efficient. This connectivity pattern has been shown improving the accuracy of patch matching. The DFR-net, with a single-tower architecture, focused on the relationship between (non-)corresponding patches, which improved the performance of the traditional Siamese network. The component of DFR-net, named RDCNet block, produces a smaller model size and is demonstrated suiting for patch matching. To ensure the experimental effectiveness, the DFR-net was trained on the public Brown patch dataset and the HPatches dataset.
Details
- Language :
- English
- ISSN :
- 21693536 and 74569708
- Volume :
- 7
- Database :
- Directory of Open Access Journals
- Journal :
- IEEE Access
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.3a74569708e047fba8d4a44b5c976af8
- Document Type :
- article
- Full Text :
- https://doi.org/10.1109/ACCESS.2019.2930003