Deep Ranking for Person Re-Identification via Joint Representation Learning

• Published in: IEEE transactions on image processing Vol. 25; no. 5; pp. 2353 - 2367
• Main Authors: Chen, Shi-Zhe, Guo, Chun-Chao, Lai, Jian-Huang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Biometric Identification - methods; Cameras; Databases, Factual; deep convolutional neural network; Feature extraction; Galleries; Humans; Image color analysis; Learning; learning to rank; Machine Learning; Measurement; Neural networks; Neural Networks (Computer); Person re-identification; Probes; Ranking; Representations; Similarity; deep convolutional neural network; Person re-identification; learning to rank
• DOI: 10.1109/TIP.2016.2545929
• ISSN: 1057-7149; 1941-0042

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 the state-of-the-art approaches, including both traditional and CNN-based methods on the challenging VIPeR, CUHK-01, and CAVIAR4REID datasets. In addition, our approach has better ability to generalize across datasets without fine-tuning.