Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification

Abstract

Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intra-sequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a de-correlation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods.

arXiv comment10 pages, 8 figures, 7 tables, accepted by CVPR 2018

References in corpus (10)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Random Erasing Data Augmentation
• Order Matters: Sequence to sequence for sets
• SVDNet for Pedestrian Retrieval
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Dataset Augmentation in Feature Space
• Quality Aware Network for Set to Set Recognition
• Deep Mutual Learning
• Neural Aggregation Network for Video Face Recognition
• DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer

Cited by in corpus (13)

• Recognizing Partial Biometric Patterns
• Parameter-Free Spatial Attention Network for Person Re-Identification
• Discriminative Feature Learning with Foreground Attention for Person Re-Identification
• Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
• Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
• Multi-scale 3D Convolution Network for Video Based Person Re-Identification
• Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
• HAT: Hierarchical Aggregation Transformers for Person Re-identification
• Temporal Knowledge Propagation for Image-to-Video Person Re-identification
• You Only Recognize Once: Towards Fast Video Text Spotting
• Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
• EgoReID Dataset: Person Re-identification in Videos Acquired by Mobile Devices with First-Person Point-of-View
• Local-Global Associative Frame Assemble in Video Re-ID