26 October 2021 Learning image embeddings without labels
Author Affiliations +
Funded by: National Natural Science Foundation of China (NSFC)
Abstract

Can we automatically learn discriminative embedding features from images when human-annotated labels are absent? The problem of unsupervised embedded learning remains a significant and open challenge in image and vision community. A joint online deep embedded clustering and hard samples mining framework are proposed to improve the representation ability of embedded learning. In addition, to enhance the discriminability of feature representations, a structure-level pair-based loss is introduced to take full advantage of structure correlation between all the mined hard samples. Finally, the quantitative results of exhaustive experiments on three benchmarks show that our proposed method performs better than existing state-of-the-art methods.

© 2021 SPIE and IS&T 1017-9909/2021/$28.00© 2021 SPIE and IS&T
Cailing Wang, Jianwei Yang, and Guoping Jiang "Learning image embeddings without labels," Journal of Electronic Imaging 30(5), 050502 (26 October 2021). https://doi.org/10.1117/1.JEI.30.5.050502
Received: 29 June 2021; Accepted: 11 October 2021; Published: 26 October 2021
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Feature extraction

Mining

Image retrieval

Data modeling

Performance modeling

Statistical analysis

Telecommunications

Back to Top