Deep Transfer Learning for Person Re-identification
This addresses the challenge of learning deep models with limited labeled data in person re-identification, offering significant performance gains over state-of-the-art methods.
The paper tackles the data sparsity problem in person re-identification by proposing deep transfer learning models, achieving Rank-1 accuracies of 85.4%, 83.7%, and 56.3% on CUHK03, Market1501, and VIPeR datasets, with an unsupervised model reaching 45.1% on VIPeR.
Person re-identification (Re-ID) poses a unique challenge to deep learning: how to learn a deep model with millions of parameters on a small training set of few or no labels. In this paper, a number of deep transfer learning models are proposed to address the data sparsity problem. First, a deep network architecture is designed which differs from existing deep Re-ID models in that (a) it is more suitable for transferring representations learned from large image classification datasets, and (b) classification loss and verification loss are combined, each of which adopts a different dropout strategy. Second, a two-stepped fine-tuning strategy is developed to transfer knowledge from auxiliary datasets. Third, given an unlabelled Re-ID dataset, a novel unsupervised deep transfer learning model is developed based on co-training. The proposed models outperform the state-of-the-art deep Re-ID models by large margins: we achieve Rank-1 accuracy of 85.4\%, 83.7\% and 56.3\% on CUHK03, Market1501, and VIPeR respectively, whilst on VIPeR, our unsupervised model (45.1\%) beats most supervised models.