Deep semantic feature matching
Estimating dense visual correspondences between objects with intra-class variation, deformations and background clutter remains a challenging problem. Thanks to the breakthrough of CNNs there are new powerful features available. Despite their easy accessibility and great success, existing semantic f...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
09 November 2017
|
| In: |
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2017, Pages: 5929-5938 |
| DOI: | 10.1109/CVPR.2017.628 |
| Subjects: | |
| Online Access: | Verlag, Volltext: http://dx.doi.org/10.1109/CVPR.2017.628
|
| Author Notes: | Nikolai Ufer and Björn Ommer |
| Summary: | Estimating dense visual correspondences between objects with intra-class variation, deformations and background clutter remains a challenging problem. Thanks to the breakthrough of CNNs there are new powerful features available. Despite their easy accessibility and great success, existing semantic flow methods could not significantly benefit from these without extensive additional training. We introduce a novel method for semantic matching with pre-trained CNN features which is based on convolutional feature pyramids and activation guided feature selection. |
|---|---|
| Item Description: | Gesehen am 13.02.2018 |
| Physical Description: | Online Resource |
| DOI: | 10.1109/CVPR.2017.628 |