Learning local descriptors with latent hard sample mining

Haiguo Gu; Yuehuan Wang

doi:10.1117/12.2557193

3 January 2020 Learning local descriptors with latent hard sample mining

Haiguo Gu, Yuehuan Wang

Proceedings Volume 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019); 1137334 (2020) https://doi.org/10.1117/12.2557193
Event: Eleventh International Conference on Graphics and Image Processing, 2019, Hangzhou, China

Abstract

Recent researches on learning local descriptor are mainly based on Convolutional Neural Network (CNN), including loss function, network architecture, sample mining, etc. In this paper, we investigated the existing datasets and difficult sample mining methods for learning local feature descriptor. And we find that the samples in the train set are often not enough for various situations. Because the changes in illumination and view are continuous, but the samples are discrete. In the meanwhile, current sample mining ways only excavate existing data of train set, which is not optimal. So we proposed a new sample mining fashion, called latent hard sample mining, which can utilize potential samples for learning. This method can mitigate the influence of inadequate training samples. We compare our approach to recently introduced convolutional local feature descriptors on Photo-tour and Hpatches dataset with different losses, and demonstrate the advantages of the proposed methods in terms of performance.

Citation Download Citation

Haiguo Gu and Yuehuan Wang "Learning local descriptors with latent hard sample mining", Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 1137334 (3 January 2020); https://doi.org/10.1117/12.2557193

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available