Deep Ranking for Person Re-identification via Joint Representation Learning

TL;DR

This paper introduces a unified deep ranking framework using CNNs for person re-identification that jointly learns features and similarity metrics, outperforming existing methods on multiple datasets.

Contribution

It presents a novel deep ranking approach that combines feature learning and metric learning into a single CNN-based framework for person re-identification.

Findings

Outperforms state-of-the-art methods on VIPeR, CUHK-01, and CAVIAR4REID datasets.

Does not rely on handcrafted features or assumptions, enabling better generalization.

Achieves higher accuracy and ranking performance in person re-identification tasks.

Abstract

This paper proposes a novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems. Although a variety of powerful algorithms have been presented in the past few years, most of them usually focus on designing hand-crafted features and learning metrics either individually or sequentially. Different from previous works, we formulate a unified deep ranking framework that jointly tackles both of these key components to maximize their strengths. We start from the principle that the correct match of the probe image should be positioned in the top rank within the whole gallery set. An effective learning-to-rank algorithm is proposed to minimize the cost corresponding to the ranking disorders of the gallery. The ranking model is solved with a deep convolutional neural network (CNN) that builds the relation between input image pairs and their similarity scores through joint representation learning directly from raw image pixels. The proposed framework allows us to get rid of feature engineering and does not rely on any assumption. An extensive comparative evaluation is given, demonstrating that our approach significantly outperforms all state-of-the-art approaches, including both traditional and CNN-based methods on the challenging VIPeR, CUHK-01 and CAVIAR4REID datasets. Additionally, our approach has better ability to generalize across datasets without fine-tuning.