HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
Yurun Tian, Axel Barroso Laguna, Tony Ng, Vassileios Balntas, Krystian Mikolajczyk
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.
BibTeX
@inproceedings{NEURIPS2020_52d2752b,
author = {Tian, Yurun and Barroso Laguna, Axel and Ng, Tony and Balntas, Vassileios and Mikolajczyk, Krystian},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {7401--7412},
publisher = {Curran Associates, Inc.},
title = {HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/52d2752b150f9c35ccb6869cbf074e48-Paper.pdf},
volume = {33},
year = {2020}
}