Learning local feature descriptors with triplets and shallow convolutional neural networks

Vassileios Balntas, Edgar Riba, Daniel Ponsa and Krystian Mikolajczyk

Abstract

It has recently been demonstrated that local feature descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Previous work on learning such descriptors has focused on exploiting pairs of positive and negative patches to learn discriminative CNN representations. In this work, we propose to utilize triplets of training samples, together with in-triplet mining of hard negatives. We show that our method achieves state of the art results, without the computational overhead typically associated with mining of negatives and with lower complexity of the network architecture. We compare our approach to recently introduced convolutional local feature descriptors, and demonstrate the advantages of the proposed methods in terms of performance and speed. We also examine different loss functions associated with triplets.

Session

Posters 2

Files

Extended Abstract (PDF, 122K)
Paper (PDF, 318K)

DOI

10.5244/C.30.119
https://dx.doi.org/10.5244/C.30.119

Citation

Bibtex

        @inproceedings{BMVC2016_119,
        	title={Learning local feature descriptors with triplets and shallow convolutional neural networks},
        	author={Vassileios Balntas, Edgar Riba, Daniel Ponsa and Krystian  Mikolajczyk},
        	year={2016},
        	month={September},
        	pages={119.1-119.11},
        	articleno={119},
        	numpages={11},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.119},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.119}
        }