Pedestrian Alignment Network For Large-scale Person Re-identification

Abstract

Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images. However, this process suffers from two types of detector errors: excessive background and part missing. Both errors deteriorate the quality of pedestrian alignment and may compromise pedestrian matching due to the position and scale variances. To address the misalignment problem, we propose that alignment can be learned from an identification procedure. We introduce the pedestrian alignment network (PAN) which allows discriminative embedding learning and pedestrian alignment without extra annotations. Our key observation is that when the convolutional neural network (CNN) learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background. The proposed

Stats

• citations311
• S2 citations—
• github stars0
• HF likes0
• heat score18.71
• arxiv keyzheng2017pedestrian

Related papers

• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• GLAD: Global-local-alignment Descriptor For Pedestrian Retrieval (2017)18.69
• Improving Person Re-identification By Attribute And Identity Learning (2017)20.71
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Part-aligned Bilinear Representations For Person Re-identification (2018)19.30