Improving Person Re-identification by Attribute and Identity Learning

Abstract

Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines.

Accepted to Pattern Recognition (PR)

References in corpus (17)

• Person Re-identification: Past, Present and Future
• A Discriminatively Learned CNN Embedding for Person Re-identification
• End-to-End Comparative Attention Networks for Person Re-identification
• Multi-task CNN Model for Attribute Prediction
• Deep Transfer Learning for Person Re-identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• Deep Ranking for Person Re-identification via Joint Representation Learning
• A Richly Annotated Dataset for Pedestrian Attribute Recognition
• Pose Invariant Embedding for Deep Person Re-identification
• Deeply-Learned Part-Aligned Representations for Person Re-Identification
• Unsupervised Person Re-identification: Clustering and Fine-tuning
• Deep Learning Face Attributes in the Wild
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Contextual Action Recognition with R*CNN
• Person Search with Natural Language Description
• Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

Cited by in corpus (104)

• In Defense of the Triplet Loss for Person Re-Identification
• Random Erasing Data Augmentation
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Dual-Path Convolutional Image-Text Embeddings with Instance Loss
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
• Deep Attention Aware Feature Learning for Person Re-Identification
• Joint Discriminative and Generative Learning for Person Re-identification
• The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
• Parameter-Efficient Person Re-identification in the 3D Space
• Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
• Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles
• Camera Style Adaptation for Person Re-identification
• Attributes Guided Feature Learning for Vehicle Re-identification
• Learning Shape Representations for Clothing Variations in Person Re-Identification
• Pedestrian Attribute Recognition: A Survey
• Receptive Multi-granularity Representation for Person Re-Identification
• Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
• Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
• Pose-Normalized Image Generation for Person Re-identification
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
• AANet: Attribute Attention Network for Person Re-Identifications
• Unsupervised Person Re-identification via Softened Similarity Learning
• Exploring the Quality of GAN Generated Images for Person Re-Identification
• ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• Densely Semantically Aligned Person Re-Identification
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
• Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
• Progressive Sample Mining and Representation Learning for One-Shot Person Re-identification with Adversarial Samples
• Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
• GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
• Spectral Feature Transformation for Person Re-identification
• Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
• Semantics-Aligned Representation Learning for Person Re-identification
• Spatial-Temporal Person Re-identification
• Describe me if you can! Characterized Instance-level Human Parsing
• Attribute-guided Feature Learning Network for Vehicle Re-identification
• Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
• Taking Modality-free Human Identification as Zero-shot Learning
• Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
• Attribute Adaptive Margin Softmax Loss using Privileged Information
• Cerberus: Attribute-based person re-identification using semantic IDs
• Person Re-identification with Metric Learning using Privileged Information
• Hierarchical Feature Embedding for Attribute Recognition
• Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks
• Prototype Completion with Primitive Knowledge for Few-Shot Learning
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• Multi-Scale Body-Part Mask Guided Attention for Person Re-identification
• Adaptive L2 Regularization in Person Re-Identification
• Adversarial Attribute-Image Person Re-identification
• End-to-End Deep Kronecker-Product Matching for Person Re-identification
• Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
• Memory Regulation and Alignment toward Generalizer RGB-Infrared Person
• Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention
• Eliminating cross-camera bias for vehicle re-identification
• HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
• Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification
• Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
• Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification
• Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
• AttKGCN: Attribute Knowledge Graph Convolutional Network for Person Re-identification
• Symmetry and Group in Attribute-Object Compositions
• Attributes-aided Part Detection and Refinement for Person Re-identification
• 3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective
• Relation Network for Person Re-identification
• A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions
• Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
• Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification
• Attribute-Aware Attention Model for Fine-grained Representation Learning
• A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
• Symbiotic Adversarial Learning for Attribute-based Person Search
• Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology
• Joint Discriminative and Metric Embedding Learning for Person Re-Identification
• Homocentric Hypersphere Feature Embedding for Person Re-identification
• Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification
• Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
• Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
• Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
• SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
• Attention Driven Person Re-identification
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
• CHD:Consecutive Horizontal Dropout for Human Gait Feature Extraction
• Learning Resolution-Invariant Deep Representations for Person Re-Identification
• Pseudo-positive regularization for deep person re-identification
• The 6th AI City Challenge
• Enhancing Person Re-identification in a Self-trained Subspace
• PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
• Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds
• Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
• Unsupervised Domain-Adaptive Person Re-identification Based on Attributes
• Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation
• Self-Paced Uncertainty Estimation for One-shot Person Re-Identification
• FlipReID: Closing the Gap between Training and Inference in Person Re-Identification