End-to-End Deep Kronecker-Product Matching for Person Re-identification

Abstract

Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re-identification. The spatial layout and correspondences between query person images are vital information for tackling this problem but are ignored by most state-of-the-art methods. In this paper, we propose a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network. A novel feature soft warping scheme is designed for aligning the feature maps based on matching results, which is shown to be crucial for achieving superior accuracy. The multi-scale features based on hourglass-like networks and self-residual attention are also exploited to further boost the re-identification performance. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach.

arXiv commentCVPR 2018 poster

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• In Defense of the Triplet Loss for Person Re-Identification
• Going Deeper with Convolutions
• Improving Person Re-identification by Attribute and Identity Learning
• Random Erasing Data Augmentation
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Stacked Hourglass Networks for Human Pose Estimation
• Deeply-Learned Part-Aligned Representations for Person Re-Identification
• SVDNet for Pedestrian Retrieval
• Multi-scale Deep Learning Architectures for Person Re-identification
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
• 3D Facial Expression Reconstruction using Cascaded Regression