A Boosting-Based Deep Distance Metric Learning Method.

Zilong Li,Daqing Gong

doi:10.1155/2022/2665843

Abstract

By leveraging neural networks, deep distance metric learning has yielded impressive results in computer vision applications. However, the existing approaches mostly focus a single deep distance metric based on pairs or triplets of samples. It is difficult for them to handle heterogeneous data and avoid overfitting. This study proposes a boosting-based learning method of multiple deep distance metrics, which generates the final distance metric through iterative training of multiple weak distance metrics. Firstly, the distance of sample pairs was mapped by a convolution neural network (CNN) and evaluated by a piecewise linear function. Secondly, the evaluation function was added as a weak learner to the boosting algorithm to generate a strong learner. Each weak learner targets the difficult samples different from the samples of previous learners. Next, an alternating optimization method was employed to train the network and loss function. Finally, the effectiveness of our method was demonstrated in contrast to state of the arts on retrieving the images from the CUB-200-2011, Cars-196, and Stanford Online Products (SOP) datasets.

Highlights

In the past decades, distance metric learning has been applied effectively in image retrieval, face recognition, person re-identification, clustering, etc
To learn deep distance metrics, many approaches have been developed based on sample pairs [2, 3], triplets [2, 4], or quadruplets [5]. is study attempts to learn the simple similarity functions of sample pairs. e distance metric was defined as the Euclidean distance between sample pairs, which can be computed rapidly compared with other metrics
The performance of the conventional distance metric was improved by introducing a piecewise linear function, which evaluates the similarity of sample pairs in distance metric learning. is facilitates the joint training of the network and loss function. rough the evaluation of various deep distance metric learning methods in the image retrieval task, it can be seen that Recall@1 of the proposed method is 4.2, 2.8, and 0.4 higher than that of the previous best score on CUB-200-2011, Cars-196, and Stanford Online Products (SOP) datasets, respectively

Summary

Introduction

Distance metric learning has been applied effectively in image retrieval, face recognition, person re-identification, clustering, etc. Some scholars resorted to ensemble technique and employed several learners to map each sample to multiple subspaces [8–10] These strategies do not support end-toend training of the network and loss function of each weak learner. The same underlying feature representation, which was pretrained through experiments, was applied to the fully connected layers of all groups In this way, the high computing cost of CNN training in the boosting framework was significantly reduced. The performance of the conventional distance metric was improved by introducing a piecewise linear function, which evaluates the similarity of sample pairs in distance metric learning. (2) A piecewise linear function was employed as the evaluation function of the distance metric of sample pairs mapped by CNN and added as a weak learner to the boosting algorithm to generate a strong learner. Literature Review is section reviews the most closely related works out of the numerous publications on the hot topic of distance metric learning

Deep Distance Metric Learning

Other Related Metric Learning

Boosting-Based Deep Distance Metric Model

Joint Training

Experiments and Results’ Analysis