This work addresses the problem of learning compact yet discriminative patch descriptors within a deep learning framework. We observe that features extracted by convolutional layers in the pixel domain are largely complementary to features extracted in a transformed domain. We propose a convolutional network framework for learning binary patch descriptors where pixel domain features are fused with features extracted from the transformed domain. In our framework, while convolutional and transformed features are distinctly extracted, they are fused and provided to a single classifier which thus jointly operates on convolutional and transformed features. We experiment at matching patches from three different datasets, showing that our feature fusion approach outperforms multiple state-of-the-art approaches in terms of accuracy, rate, and complexity.
@article{arxiv.1901.03547,
title = {Feature Fusion for Robust Patch Matching With Compact Binary Descriptors},
author = {Andrea Migliorati and Attilio Fiandrotti and Gianluca Francini and Skjalg Lepsoy and Riccardo Leonardi},
journal= {arXiv preprint arXiv:1901.03547},
year = {2019}
}
Comments
MMSP 2018 - IEEE 20th International Workshop on Multimedia Signal Processing - August 29-31 2018, Vancouver, Canada