Skip to Main content Skip to Navigation
Journal articles

Learnable Descriptors for Visual Search

Abstract : This work proposes LDVS, a learnable binary local descriptor devised for matching natural images within the MPEG CDVS framework. LDVS descriptors are learned so that they can be sign-quantized and compared using the Hamming distance. The underlying convolutional architecture enjoys a moderate parameters count for operations on mobile devices. Our experiments show that LDVS descriptors perform favorably over comparable learned binary descriptors at patch matching on two different datasets. A complete pair-wise image matching pipeline is then designed around LDVS descriptors, integrating them in the reference CDVS evaluation framework. Experiments show that LDVS descriptors outperform the compressed CDVS SIFT-like descriptors at pair-wise image matching over the challenging CDVS image dataset.
Document type :
Journal articles
Complete list of metadata

https://hal.telecom-paris.fr/hal-03245174
Contributor : Attilio Fiandrotti Connect in order to contact the contributor
Submitted on : Monday, February 28, 2022 - 2:53:50 PM
Last modification on : Friday, April 1, 2022 - 3:53:42 AM
Long-term archiving on: : Sunday, May 29, 2022 - 6:04:33 PM

File

09238464 (1).pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Andrea Migliorati, Attilio Fiandrotti, Gianluca Francini, Riccardo Leonardi. Learnable Descriptors for Visual Search. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2021, 30, pp.80 - 91. ⟨10.1109/tip.2020.3031216⟩. ⟨hal-03245174⟩

Share

Metrics

Record views

8

Files downloads

15