Triplet Permutation Method for Deep Learning of Single-Shot Person Re-Identification

TL;DR

This paper introduces the Triplet Permutation method, a novel data augmentation strategy for deep learning in single-shot person re-identification, effectively reducing overfitting and improving performance on challenging datasets.

Contribution

The paper proposes a new Triplet Permutation technique to generate multiple training sets, enhancing deep learning models for single-shot person re-identification.

Findings

Improved re-identification accuracy on PRID2011 dataset.

Effective reduction of overfitting in triplet network training.

Demonstrated superiority over existing methods.

Abstract

Solving Single-Shot Person Re-Identification (Re-Id) by training Deep Convolutional Neural Networks is a daunting challenge, due to the lack of training data, since only two images per person are available. This causes the overfitting of the models, leading to degenerated performance. This paper formulates the Triplet Permutation method to generate multiple training sets, from a certain re-id dataset. This is a novel strategy for feeding triplet networks, which reduces the overfitting of the Single-Shot Re-Id model. The improved performance has been demonstrated over one of the most challenging Re-Id datasets, PRID2011, proving the effectiveness of the method.