English

Learning Generalized Hybrid Proximity Representation for Image Recognition

Computer Vision and Pattern Recognition 2023-04-21 v2 Machine Learning Probability Machine Learning

Abstract

Recently, deep metric learning techniques received attention, as the learned distance representations are useful to capture the similarity relationship among samples and further improve the performance of various of supervised or unsupervised learning tasks. We propose a novel supervised metric learning method that can learn the distance metrics in both geometric and probabilistic space for image recognition. In contrast to the previous metric learning methods which usually focus on learning the distance metrics in Euclidean space, our proposed method is able to learn better distance representation in a hybrid approach. To achieve this, we proposed a Generalized Hybrid Metric Loss (GHM-Loss) to learn the general hybrid proximity features from the image data by controlling the trade-off between geometric proximity and probabilistic proximity. To evaluate the effectiveness of our method, we first provide theoretical derivations and proofs of the proposed loss function, then we perform extensive experiments on two public datasets to show the advantage of our method compared to other state-of-the-art metric learning methods.

Keywords

Cite

@article{arxiv.2301.13459,
  title  = {Learning Generalized Hybrid Proximity Representation for Image Recognition},
  author = {Zhiyuan Li and Anca Ralescu},
  journal= {arXiv preprint arXiv:2301.13459},
  year   = {2023}
}

Comments

The paper has been accepted by the IEEE ICTAI 2022

R2 v1 2026-06-28T08:27:43.888Z