# Quadruplet Selection Methods for Deep Embedding Learning

## TL;DR

This paper introduces a novel quadruplet selection method for deep embedding learning that leverages hierarchical labels and hard negative mining to improve fine-grained object recognition accuracy.

## Contribution

It proposes a new feature selection approach for quadruplet training samples that enhances embedding quality and recognition performance in fine-grained classification tasks.

## Key findings

- Hard negative sample selection improves recognition metrics.
- The proposed method outperforms state-of-the-art approaches.
- Hierarchical labels aid in effective quadruplet formation.

## Abstract

Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep embedding learning by using a multi-task learning framework, in which the hierarchical labels (coarse and fine labels) of the samples are utilized both for classification and a quadruplet-based loss function. In order to improve the recognition strength of the learned features, we present a novel feature selection method specifically designed for four training samples of a quadruplet. By experiments, it is observed that the selection of very hard negative samples with relatively easy positive ones from the same coarse and fine classes significantly increases some performance metrics in a fine-grained dataset when compared to selecting the quadruplet samples randomly. The feature embedding learned by the proposed method achieves favorable performance against its state-of-the-art counterparts.