Deep Transfer Learning for Person Re-identification

Abstract

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.

12 pages, 2 figures

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Domain Adaptation by Backpropagation
• Person Re-identification: Past, Present and Future
• Deep Transfer Network: Unsupervised Domain Adaptation

Cited by in corpus (17)

• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• Pose-driven Deep Convolutional Model for Person Re-identification
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset
• Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
• Omni-directional Feature Learning for Person Re-identification
• Weakly supervised discriminative feature learning with state information for person identification
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN
• Person Re-identification with Adversarial Triplet Embedding
• Imbalance Robust Softmax for Deep Embeeding Learning
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification