Multiregion Bilinear Convolutional Neural Networks for Person Re-Identification

TL;DR

This paper introduces a multiregion bilinear CNN architecture for person re-identification that balances spatial information retention with feature embedding, outperforming existing methods on key benchmarks.

Contribution

It proposes a novel multiregion bilinear pooling approach that improves person re-identification accuracy over previous bilinear CNN models.

Findings

Outperforms baseline models on Market-1501, CUHK01, CUHK03 datasets.

Achieves state-of-the-art results on two datasets.

Demonstrates the effectiveness of local bilinear pooling for re-identification.

Abstract

In this work we propose a new architecture for person re-identification. As the task of re-identification is inherently associated with embedding learning and non-rigid appearance description, our architecture is based on the deep bilinear convolutional network (Bilinear-CNN) that has been proposed recently for fine-grained classification of highly non-rigid objects. While the last stages of the original Bilinear-CNN architecture completely removes the geometric information from consideration by performing orderless pooling, we observe that a better embedding can be learned by performing bilinear pooling in a more local way, where each pooling is confined to a predefined region. Our architecture thus represents a compromise between traditional convolutional networks and bilinear CNNs and strikes a balance between rigid matching and completely ignoring spatial information. We perform the experimental validation of the new architecture on the three popular benchmark datasets (Market-1501, CUHK01, CUHK03), comparing it to baselines that include Bilinear-CNN as well as prior art. The new architecture outperforms the baseline on all three datasets, while performing better than state-of-the-art on two out of three. The code and the pretrained models of the approach can be found at https://github.com/madkn/MultiregionBilinearCNN-ReId.