HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
Abstract
In this paper, we investigate how L2 normalisation affects the back-propagated descriptor gradients during training. Based on our observations, we propose HyNet, a new local descriptor that leads to state-of-the-art results in matching. HyNet introduces a hybrid similarity measure for triplet margin loss, a regularisation term constraining the descriptor norm, and a new network architecture that performs L2 normalisation of all intermediate feature maps and the output descriptors. HyNet surpasses previous methods by a significant margin on standard benchmarks that include patch matching, verification, and retrieval, as well as outperforming full end-to-end methods on 3D reconstruction tasks.
Cite
Text
Tian et al. "HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss." Neural Information Processing Systems, 2020.Markdown
[Tian et al. "HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/tian2020neurips-hynet/)BibTeX
@inproceedings{tian2020neurips-hynet,
title = {{HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss}},
author = {Tian, Yurun and Laguna, Axel Barroso and Ng, Tony and Balntas, Vassileios and Mikolajczyk, Krystian},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/tian2020neurips-hynet/}
}