Learning Generalized Hybrid Proximity Representation for Image Recognition

TL;DR

This paper introduces a supervised metric learning approach that combines geometric and probabilistic spaces to improve image recognition, using a novel loss function and extensive experiments to demonstrate its effectiveness.

Contribution

It proposes a Generalized Hybrid Metric Loss that learns hybrid proximity features, integrating geometric and probabilistic distances for enhanced image recognition.

Findings

Outperforms state-of-the-art metric learning methods on public datasets.

Provides theoretical derivations and proofs for the proposed loss function.

Demonstrates improved accuracy in image recognition tasks.

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.