Joint Discriminative and Generative Learning for Person Re-identification

Abstract

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.

CVPR 2019 (Oral). Add transfer learning results

References in corpus (13)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Instance Normalization: The Missing Ingredient for Fast Stylization
• In Defense of the Triplet Loss for Person Re-Identification
• Person Re-identification: Past, Present and Future
• Improving Person Re-identification by Attribute and Identity Learning
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Which Training Methods for GANs do actually Converge?
• Pose Guided Person Image Generation
• Pedestrian Alignment Network for Large-scale Person Re-identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations

Cited by in corpus (11)

• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• Adaptive Exploration for Unsupervised Person Re-Identification
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Learning Shape Representations for Clothing Variations in Person Re-Identification
• Unsupervised Person Re-identification via Softened Similarity Learning
• SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
• Unity Style Transfer for Person Re-Identification
• Memory Regulation and Alignment toward Generalizer RGB-Infrared Person
• Towards Precise Intra-camera Supervised Person Re-identification
• Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
• Energy Clustering for Unsupervised Person Re-identification