H-Patches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00344086" target="_blank" >RIV/68407700:21230/20:00344086 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/TPAMI.2019.2915233" target="_blank" >https://doi.org/10.1109/TPAMI.2019.2915233</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2019.2915233" target="_blank" >10.1109/TPAMI.2019.2915233</a>

Result language

angličtina

Original language name

H-Patches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors

Original language description

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.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

1939-3539

Volume of the periodical

42

Issue of the periodical within the volume

11

Country of publishing house

US - UNITED STATES

Number of pages

17

Pages from-to

2825-2841

UT code for WoS article

000575381000007

EID of the result in the Scopus database

2-s2.0-85092510856