Imperial College London

DrKrystianMikolajczyk

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 6220k.mikolajczyk

 
 
//

Location

 

Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Balntas:2019:10.1109/tpami.2019.2915233,
author = {Balntas, V and Lenc, K and Vedaldi, A and Tuytelaars, T and Matas, J and Mikolajczyk, K},
doi = {10.1109/tpami.2019.2915233},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {1--1},
title = {HPatches: A benchmark and evaluation of handcrafted and learned local descriptors},
url = {http://dx.doi.org/10.1109/tpami.2019.2915233},
year = {2019}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - In this paper, a novel benchmark is introduced for evaluating local image descriptors. We demonstrate limitations of the commonly used datasets and evaluation protocols, that lead to ambiguities and contradictory results in the literature. Furthermore, these benchmarks are nearly saturated due to the recent improvements in local descriptors obtained by learning from large annotated datasets. To address these issues, we introduce a new large dataset suitable for training and testing modern descriptors, together with strictly defined evaluation protocols in several tasks such as matching, retrieval and verification. This allows for more realistic, thus more reliable comparisons in different application scenarios. We evaluate the performance of several state-of-the-art descriptors and analyse their properties. We show that a simple normalisation of traditional hand-crafted descriptors is able to boost their performance to the level of deep learning based descriptors once realistic benchmarks are considered. Additionally we specify a protocol for learning and evaluating using cross validation. We show that when training state-of-the-art descriptors on this dataset, the traditional verification task is almost entirely saturated.
AU - Balntas,V
AU - Lenc,K
AU - Vedaldi,A
AU - Tuytelaars,T
AU - Matas,J
AU - Mikolajczyk,K
DO - 10.1109/tpami.2019.2915233
EP - 1
PY - 2019///
SN - 0162-8828
SP - 1
TI - HPatches: A benchmark and evaluation of handcrafted and learned local descriptors
T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence
UR - http://dx.doi.org/10.1109/tpami.2019.2915233
UR - https://ieeexplore.ieee.org/document/8712555
UR - http://hdl.handle.net/10044/1/77898
ER -