• DOI:10.1016/j.patrec.2020.03.020
Corpus ID: 216238565

DIABLO: Dictionary-based Attention Block for Deep Metric Learning

@article{Jacob2020DIABLODA,
  title={DIABLO: Dictionary-based Attention Block for Deep Metric Learning},
  author={P. Jacob and D. Picard and A. Histace and E. Klein},
  journal={Pattern Recognit. Lett.},
  year={2020},
  volume={135},
  pages={99-105}
}

P. Jacob, D. Picard, +1 author E. Klein

Published 2020

Computer Science

Pattern Recognit. Lett.

Abstract Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation. In this paper, we propose DIABLO, a dictionary-based attention method for image… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed