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 (6)

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

Cited by in corpus (52)

• In Defense of the Triplet Loss for Person Re-Identification
• Improving Person Re-identification by Attribute and Identity Learning
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• 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
• SVDNet for Pedestrian Retrieval
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Second-order Non-local Attention Networks for Person Re-identification
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• Attention-Aware Compositional Network for Person Re-identification
• The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
• ABD-Net: Attentive but Diverse Person Re-Identification
• Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
• Learning Generalisable Omni-Scale Representations for Person Re-Identification
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• Pose-driven Deep Convolutional Model for Person Re-identification
• Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
• Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
• Self-supervised Multi-view Person Association and Its Applications
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Densely Semantically Aligned Person Re-Identification
• Self-training with progressive augmentation for unsupervised cross-domain person re-identification
• Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification
• An Evaluation of Deep CNN Baselines for Scene-Independent 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
• LVreID: Person Re-Identification with Long Sequence Videos
• Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• C-Net: A Reliable Convolutional Neural Network for Biomedical Image Classification
• Segmentation Mask Guided End-to-End Person Search
• In Defense of the Classification Loss for Person Re-Identification
• Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset
• A Strong Baseline for Fashion Retrieval with Person Re-Identification Models
• Homocentric Hypersphere Feature Embedding for Person Re-identification
• Omni-directional Feature Learning for Person Re-identification
• Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
• SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
• Learning Deep Representations by Mutual Information for Person Re-identification
• Weakly supervised discriminative feature learning with state information for person identification
• Deep Person Re-Identification with Improved Embedding and Efficient Training
• Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
• Sparse Label Smoothing Regularization for Person Re-Identification
• Imbalance Robust Softmax for Deep Embeeding Learning
• Person Re-identification with Adversarial Triplet Embedding
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN