Ensemble Feature for Person Re-Identification

TL;DR

This paper introduces EnsembleNet, a multi-branch CNN architecture based on ResNet-50, that enhances person re-identification by combining features from multiple branches, achieving state-of-the-art results on key benchmarks.

Contribution

The paper proposes a novel ensemble network architecture for person re-ID that improves feature robustness and discriminability over single CNN models.

Findings

Achieves state-of-the-art performance on Market1501, DukeMTMC-reID, CUHK03 datasets.

Uses shared backbone to reduce computation and memory costs.

Ensemble features improve person re-identification accuracy.

Abstract

In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this problem. The features extracted by convolutional neural networks (CNN) are more effective and discriminative than the hand-crafted features. However, deep feature extracted by a single CNN network is not robust enough in testing stage. To improve the ability of feature representation, we propose a new ensemble network (EnsembleNet) by dividing a single network into multiple end-to-end branches. The ensemble feature is obtained by concatenating each of the branch features to represent a person. EnsembleNet is designed based on ResNet-50 and its backbone shares most of the parameters for saving computation and memory cost. Experimental results show that our EnsembleNet achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.