AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

Abstract

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.

arXiv comment9 pages, 8 figures

References in corpus (23)

• 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
• Deep Representation Learning with Part Loss for Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Xception: Deep Learning with Depthwise Separable Convolutions
• Deep Transfer Learning for Person Re-identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Pose Invariant Embedding for Deep Person Re-identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• Beyond triplet loss: a deep quadruplet network for person re-identification
• Re-ranking Person Re-identification with k-reciprocal Encoding
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Quality Aware Network for Set to Set Recognition
• Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets
• Deep Mutual Learning
• Scalable Person Re-identification on Supervised Smoothed Manifold
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• Neural Person Search Machines
• Learning Compact Appearance Representation for Video-based Person Re-Identification
• Cross Domain Knowledge Transfer for Person Re-identification
• Video-based Person Re-identification with Accumulative Motion Context

Cited by in corpus (72)

• SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
• JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• Omni-Scale Feature Learning for Person Re-Identification
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• Recognizing Partial Biometric Patterns
• Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
• Parameter-Efficient Person Re-identification in the 3D Space
• Horizontal Pyramid Matching for Person Re-identification
• Group Re-Identification with Multi-grained Matching and Integration
• Feature Completion Transformer for Occluded Person Re-identification
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Relation-Aware Global Attention for Person Re-identification
• Domain Adaptive Person Re-Identification via Coupling Optimization
• Identity-Guided Human Semantic Parsing for Person Re-Identification
• EANet: Enhancing Alignment for Cross-Domain Person Re-identification
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification
• Pose-guided Visible Part Matching for Occluded Person ReID
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Style Alignment based Dynamic Observation Method for UAV-View Geo-localization
• Batch DropBlock Network for Person Re-identification and Beyond
• Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
• Densely Semantically Aligned Person Re-Identification
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
• Knowledge Distillation for End-to-End Person Search
• Self-training with progressive augmentation for unsupervised cross-domain person re-identification
• Generalizable Person Re-identification with Relevance-aware Mixture of Experts
• Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification
• Semantics-Aligned Representation Learning for Person Re-identification
• FlowMOT: 3D Multi-Object Tracking by Scene Flow Association
• Hetero-Center Loss for Cross-Modality Person Re-Identification
• Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
• Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
• Real-time Person Re-identification at the Edge: A Mixed Precision Approach
• Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
• A Person Re-identification Data Augmentation Method with Adversarial Defense Effect
• Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification
• ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
• Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification
• Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models
• Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
• Adaptive L2 Regularization in Person Re-Identification
• Multi-Scale Body-Part Mask Guided Attention for Person Re-identification
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
• Adaptive Re-ranking of Deep Feature for Person Re-identification
• Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• In Defense of the Classification Loss for Person Re-Identification
• Re-Identification Supervised Texture Generation
• PGGANet: Pose Guided Graph Attention Network for Person Re-identification
• Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Cameras
• Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology
• Combining Two Adversarial Attacks Against Person Re-Identification Systems
• Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features
• Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification
• Progressive Learning Algorithm for Efficient Person Re-Identification
• MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification
• Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
• Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
• Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
• Knowledge Transfer Graph for Deep Collaborative Learning
• Learning Incremental Triplet Margin for Person Re-identification
• Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
• Bridging the Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalization
• Single Camera Training for Person Re-identification
• Cross-Resolution Person Re-identification with Deep Antithetical Learning
• VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN
• A Generic Object Re-identification System for Short Videos