End-to-End Training of CNN Ensembles for Person Re-Identification

TL;DR

This paper introduces an end-to-end ensemble approach using DenseNet for person re-identification, effectively reducing overfitting and achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel ensemble learning framework that creates diverse base learners within a single DenseNet, improving re-identification accuracy and computational efficiency.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively reduces overfitting, especially on small datasets.

Computationally efficient due to shared dense blocks.

Abstract

We propose an end-to-end ensemble method for person re-identification (ReID) to address the problem of overfitting in discriminative models. These models are known to converge easily, but they are biased to the training data in general and may produce a high model variance, which is known as overfitting. The ReID task is more prone to this problem due to the large discrepancy between training and test distributions. To address this problem, our proposed ensemble learning framework produces several diverse and accurate base learners in a single DenseNet. Since most of the costly dense blocks are shared, our method is computationally efficient, which makes it favorable compared to the conventional ensemble models. Experiments on several benchmark datasets demonstrate that our method achieves state-of-the-art results. Noticeable performance improvements, especially on relatively small datasets, indicate that the proposed method deals with the overfitting problem effectively.