English

IDEAL: Independent Domain Embedding Augmentation Learning

Computer Vision and Pattern Recognition 2021-05-24 v1 Artificial Intelligence

Abstract

Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this paper, we develop a novel mechanism, the independent domain embedding augmentation learning ({IDEAL}) method. It can simultaneously learn multiple independent embedding spaces for multiple domains generated by predefined data transformations. Our IDEAL is orthogonal to existing DML techniques and can be seamlessly combined with prior DML approaches for enhanced performance. Empirical results on visual retrieval tasks demonstrate the superiority of the proposed method. For example, the IDEAL improves the performance of MS loss by a large margin, 84.5\% \rightarrow 87.1\% on Cars-196, and 65.8\% \rightarrow 69.5\% on CUB-200 at Recall@1@1. Our IDEAL with MS loss also achieves the new state-of-the-art performance on three image retrieval benchmarks, \ie, \emph{Cars-196}, \emph{CUB-200}, and \emph{SOP}. It outperforms the most recent DML approaches, such as Circle loss and XBM, significantly. The source code and pre-trained models of our method will be available at\emph{\url{https://github.com/emdata-ailab/IDEAL}}.

Keywords

Cite

@article{arxiv.2105.10112,
  title  = {IDEAL: Independent Domain Embedding Augmentation Learning},
  author = {Zhiyuan Chen and Guang Yao and Wennan Ma and Lin Xu},
  journal= {arXiv preprint arXiv:2105.10112},
  year   = {2021}
}

Comments

11 pages, 2 figures, 4 tables

R2 v1 2026-06-24T02:19:36.683Z