Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification

Abstract

Person re-identification (re-id) aims to match pedestrians observed by disjoint camera views. It attracts increasing attention in computer vision due to its importance to surveillance system. To combat the major challenge of cross-view visual variations, deep embedding approaches are proposed by learning a compact feature space from images such that the Euclidean distances correspond to their cross-view similarity metric. However, the global Euclidean distance cannot faithfully characterize the ideal similarity in a complex visual feature space because features of pedestrian images exhibit unknown distributions due to large variations in poses, illumination and occlusion. Moreover, intra-personal training samples within a local range are robust to guide deep embedding against uncontrolled variations, which however, cannot be captured by a global Euclidean distance. In this paper, we study the problem of person re-id by proposing a novel sampling to mine suitable \textit{positives} (i.e. intra-class) within a local range to improve the deep embedding in the context of large intra-class variations. Our method is capable of learning a deep similarity metric adaptive to local sample structure by minimizing each sample's local distances while propagating through the relationship between samples to attain the whole intra-class minimization. To this end, a novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep embedding. This yields local discriminations by selecting local-ranged positive samples, and the learned features are robust to dramatic intra-class variations. Experiments on benchmarks show state-of-the-art results achieved by our method.

Published on Pattern Recognition

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning Face Representation by Joint Identification-Verification
• Compressing Deep Convolutional Networks using Vector Quantization
• SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
• CNN: Single-label to Multi-label
• Learning Deep Embeddings with Histogram Loss
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Deep Ranking for Person Re-identification via Joint Representation Learning
• Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
• Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering
• Local Similarity-Aware Deep Feature Embedding
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
• Embedding Deep Metric for Person Re-identication A Study Against Large Variations
• A Siamese Long Short-Term Memory Architecture for Human Re-Identification
• Scalable Person Re-identification on Supervised Smoothed Manifold
• Random Forests for Metric Learning with Implicit Pairwise Position Dependence
• Nonlinear Local Metric Learning for Person Re-identification

Cited by in corpus (56)

• Improving Person Re-identification by Attribute and Identity Learning
• Binary Neural Networks: A Survey
• Multi-View Spectral Clustering via Structured Low-Rank Matrix Factorization
• Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
• Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Minimum Margin Loss for Deep Face Recognition
• Hierarchical Information Quadtree: Efficient Spatial Temporal Image Search for Multimedia Stream
• Distance-based Camera Network Topology Inference for Person Re-identification
• An Introduction to Person Re-identification with Generative Adversarial Networks
• Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Deep Instance-Level Hard Negative Mining Model for Histopathology Images
• Hierarchical One Permutation Hashing: Efficient Multimedia Near Duplicate Detection
• Exploring Reciprocal Attention for Salient Object Detection by Cooperative Learning
• Understanding and Exploiting Dependent Variables with Deep Metric Learning
• Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings
• Saliency guided deep network for weakly-supervised image segmentation
• Self-Attention Recurrent Network for Saliency Detection
• Deep neural network-based classification model for Sentiment Analysis
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Weakly Supervised Person Re-Identification
• Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation
• End-to-End Training of CNN Ensembles for Person Re-Identification
• Person Re-Identification using Deep Learning Networks: A Systematic Review
• Guiding Intelligent Surveillance System by learning-by-synthesis gaze estimation
• Efficient Region of Visual Interests Search for Geo-multimedia Data
• An Efficient Approach for Geo-Multimedia Cross-Modal Retrieval
• Efficient Interactive Search for Geo-tagged Multimedia Data
• Hierarchical Attention Network for Action Segmentation
• CNN-VWII: An Efficient Approach for Large-Scale Video Retrieval by Image Queries
• The combination of context information to enhance simple question answering
• Self-Weighted Multiview Metric Learning by Maximizing the Cross Correlations
• Marrying Tracking with ELM: A Metric Constraint Guided Multiple Feature Fusion Method
• Efficient Multimedia Similarity Measurement Using Similar Elements
• Co-regularized Multi-view Sparse Reconstruction Embedding for Dimension Reduction
• Using Context Information to Enhance Simple Question Answering
• Efficient Continuous Top-$k$ Geo-Image Search on Road Network
• Graph-based Multi-view Binary Learning for Image Clustering
• Robust Tracking via Weighted Online Extreme Learning Machine
• A Filter of Minhash for Image Similarity Measures
• Temporal Activity Path Based Character Correction in Social Networks
• TPM: A GPS-based Trajectory Pattern Mining System
• Auto-weighted Mutli-view Sparse Reconstructive Embedding
• A hybrid index model for efficient spatio-temporal search in HBase
• Efficient Top K Temporal Spatial Keyword Search
• Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval
• Density-Adaptive Kernel based Efficient Reranking Approaches for Person Reidentification
• Anomaly detecting and ranking of the cloud computing platform by multi-view learning
• Fast Pedestrian Detection based on T-CENTRIST in infrared image
• Topic representation: finding more representative words in topic models
• GPU based Parallel Optimization for Real Time Panoramic Video Stitching
• HOC-Tree: A Novel Index for efficient Spatio-temporal Range Search