Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns

TL;DR

This paper introduces TFusion, an unsupervised incremental learning method that transfers visual classifiers and learns spatial-temporal patterns to improve person re-identification across different datasets in real-world surveillance scenarios.

Contribution

The paper presents a novel transfer learning approach that combines visual features with spatial-temporal patterns using Bayesian fusion for cross-dataset person re-identification.

Findings

Significant performance improvements over existing methods

Effective transfer of classifiers from labeled to unlabeled datasets

Robustness demonstrated across multiple real surveillance datasets

Abstract

Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting. It is challenging to incrementally optimize the models by using the abundant unlabeled data collected from the target domain. To address this challenge, we propose an unsupervised incremental learning algorithm, TFusion, which is aided by the transfer learning of the pedestrians' spatio-temporal patterns in the target domain. Specifically, the algorithm firstly transfers the visual classifier trained from small labeled source dataset to the unlabeled target dataset so as to learn the pedestrians' spatial-temporal patterns. Secondly, a Bayesian fusion model is proposed to combine the learned spatio-temporal patterns with visual features to achieve a significantly improved classifier. Finally, we propose a learning-to-rank based mutual promotion procedure to incrementally optimize the classifiers based on the unlabeled data in the target domain. Comprehensive experiments based on multiple real surveillance datasets are conducted, and the results show that our algorithm gains significant improvement compared with the state-of-art cross-dataset unsupervised person re-identification algorithms.