Deep Ranking for Person Re-identification via Joint Representation Learning

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.

15 pages, 15 figures, IEEE Transactions on Image Processing (TIP), 2016

References in corpus (2)

• CNN: Single-label to Multi-label
• DISC: Deep Image Saliency Computing via Progressive Representation Learning

Cited by in corpus (14)

• Improving Person Re-identification by Attribute and Identity Learning
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• Adaptive Exploration for Unsupervised Person Re-Identification
• Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Learning View-Specific Deep Networks for Person Re-Identification
• Learning Correspondence Structures for Person Re-identification
• Group Re-Identification with Multi-grained Matching and Integration
• Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval
• CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
• Cross-Camera Trajectories Help Person Retrieval in a Camera Network