Deep-Person: Learning Discriminative Deep Features for Person Re-Identification

Abstract

Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor. However, the spatial context between these parts is ignored for the independent extractor to each separate part. In this paper, we propose to apply Long Short-Term Memory (LSTM) in an end-to-end way to model the pedestrian, seen as a sequence of body parts from head to foot. Integrating the contextual information strengthens the discriminative ability of local representation. We also leverage the complementary information between local and global feature. Furthermore, we integrate both identification task and ranking task in one network, where a discriminative embedding and a similarity measurement are learned concurrently. This results in a novel three-branch framework named Deep-Person, which learns highly discriminative features for person Re-ID. Experimental results demonstrate that Deep-Person outperforms the state-of-the-art methods by a large margin on three challenging datasets including Market-1501, CUHK03, and DukeMTMC-reID. Specifically, combining with a re-ranking approach, we achieve a 90.84% mAP on Market-1501 under single query setting.

arXiv commentAccepted to Pattern Recognition. The code is released: https://github.com/zydou/Deep-Person

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Person Re-identification: Past, Present and Future
• Improving Person Re-identification by Attribute and Identity Learning
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Deep Transfer Learning for Person Re-identification
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification

Cited by in corpus (12)

• Horizontal Pyramid Matching for Person Re-identification
• Relation-Aware Global Attention for Person Re-identification
• Survey on Deep Learning Techniques for Person Re-Identification Task
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Densely Semantically Aligned Person Re-Identification
• Semantics-Aligned Representation Learning for Person Re-identification
• Hetero-Center Loss for Cross-Modality Person Re-Identification
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• Relation Network for Person Re-identification
• Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology
• Progressive Learning Algorithm for Efficient Person Re-Identification
• Learning Incremental Triplet Margin for Person Re-identification