Multi-Domain Adversarial Feature Generalization for Person Re-Identification
Open Access
- 31 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 1596-1607
Abstract
With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models trained on a single dataset usually suffer from considerable performance degradation when applied to videos of a different camera network. To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain. However, these approaches still require the unlabeled data of the target domain during the training process, making them impractical. A practical Person Re-ID system pre-trained on other datasets should start running immediately after deployment on a new site without having to wait until sufficient images or videos are collected and the pre-trained model is tuned. To serve this purpose, in this paper, we reformulate person re-identification as a multi-dataset domain generalization problem. We propose a multi-dataset feature generalization network (MMFA-AAE), which is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to ‘unseen’ camera systems. The network is based on an adversarial auto-encoder to learn a generalized domain-invariant latent feature representation with the Maximum Mean Discrepancy (MMD) measure to align the distributions across multiple domains. Extensive experiments demonstrate the effectiveness of the proposed method. Our MMFA-AAE approach not only outperforms most of the domain generalization Person Re-ID methods, but also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.Keywords
All Related Versions
Funding Information
- EU Horizon 2020 Marie Sklodowska-Curie Actions through the Project entitled Computer Vision Enabled Multimedia Forensics and People Identification (690907)
- National Research Foundation, Singapore, under its AI Singapore Programme (AISG) with the Defence Science and Technology Agency, Singapore (AISG-100E-2018-018, DST000ECI19300431)
This publication has 37 references indexed in Scilit:
- Deep Transfer Metric LearningIEEE Transactions on Image Processing, 2016
- Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification2016
- Learning a Discriminative Null Space for Person Re-identification2016
- Scalable Person Re-identification: A Benchmark2015
- Domain Generalization for Object Recognition with Multi-task Autoencoders2015
- Learning to rank in person re-identification with metric ensembles2015
- Cross-Domain Person Reidentification Using Domain Adaptation Ranking SVMsIEEE Transactions on Image Processing, 2015
- Domain transfer for person re-identification2013
- Person Re-identification by Descriptive and Discriminative Classification2011
- Associating Groups of People2009