PersonNet: Person Re-identification with Deep Convolutional Neural Networks

Abstract

In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a similarity value indicating whether the two input images depict the same person. A layer of computing neighborhood range differences across two input images is employed to capture local relationship between patches. This operation is to seek a robust feature from input images. By increasing the depth to 10 weight layers and using very small (3$\times$3) convolution filters, our architecture achieves a remarkable improvement on the prior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into our architecture, which is beneficial to deep nets. Our method consistently outperforms state-of-the-art on two large datasets (CUHK03 and Market-1501), and a medium-sized data set (CUHK01).

7 pages. Fixed Figure 4 (a)

Cited by in corpus (41)

• Person Re-identification: Past, Present and Future
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Beyond triplet loss: a deep quadruplet network for person re-identification
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
• Attention-Aware Compositional Network for Person Re-identification
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Pose-driven Deep Convolutional Model for Person Re-identification
• Camera Style Adaptation for Person Re-identification
• Survey on Deep Learning Techniques for Person Re-Identification Task
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
• Neural Person Search Machines
• Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?
• Densely Semantically Aligned Person Re-Identification
• View Confusion Feature Learning for Person Re-identification
• Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
• Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• Segmentation Mask Guided End-to-End Person Search
• Deep Hybrid Similarity Learning for Person Re-identification
• Three-Stream Convolutional Networks for Video-based Person Re-Identification
• In Defense of the Classification Loss for Person Re-Identification
• Support Neighbor Loss for Person Re-Identification
• Spatial-Aware GAN for Unsupervised Person Re-identification
• Homocentric Hypersphere Feature Embedding for Person Re-identification
• Temporal Action Detection by Joint Identification-Verification
• Triplet-based Deep Similarity Learning for Person Re-Identification
• Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification
• Pseudo-positive regularization for deep person re-identification
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN