A Discriminatively Learned CNN Embedding for Person Re-identification

Abstract

We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a new siamese network that simultaneously computes identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the annotations. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning Face Representation by Joint Identification-Verification
• Person Re-identification: Past, Present and Future
• DeepID3: Face Recognition with Very Deep Neural Networks
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Deep Transfer Learning for Person Re-identification
• Deep Metric Learning for Practical Person Re-Identification
• Learning a Discriminative Null Space for Person Re-identification
• Person Re-identification Meets Image Search
• Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification
• Person Re-identification in the Wild
• SIFT Meets CNN: A Decade Survey of Instance Retrieval
• Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

Cited by in corpus (103)

• In Defense of the Triplet Loss for Person Re-Identification
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
• Improving Person Re-identification by Attribute and Identity Learning
• A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Dual-Path Convolutional Image-Text Embeddings with Instance Loss
• Deep Representation Learning with Part Loss for Person Re-Identification
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• Few-Example Object Detection with Model Communication
• STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
• Adaptive Exploration for Unsupervised Person Re-Identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• SVDNet for Pedestrian Retrieval
• Person Re-identification in Aerial Imagery
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• TransReID: Transformer-based Object 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
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Unsupervised Semantic-based Aggregation of Deep Convolutional Features
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• Neural Multi-Atlas Label Fusion: Application to Cardiac MR Images
• Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
• Camera Style Adaptation for Person Re-identification
• Person Re-Identification by Semantic Region Representation and Topology Constraint
• Learning Shape Representations for Clothing Variations in Person Re-Identification
• Pose-Normalized Image Generation for Person Re-identification
• Batch DropBlock Network for Person Re-identification and Beyond
• Multilinear subspace learning for person re-identification based fusion of high order tensor features
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
• Exploring the Quality of GAN Generated Images for Person Re-Identification
• Physical Adversarial Attacks for Surveillance: A Survey
• Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation
• A heterogeneous branch and multi-level classification network for person re-identification
• SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
• Compact Network Training for Person ReID
• Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
• University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
• DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
• Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification
• DCDLearn: Multi-order Deep Cross-distance Learning for Vehicle Re-Identification
• Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
• Learning Context Graph for Person Search
• Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations
• Grafted network for person re-identification
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
• Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
• Long-Term Cloth-Changing Person Re-identification
• GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
• Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification
• Eliminating cross-camera bias for vehicle re-identification
• Multi-view Drone-based Geo-localization via Style and Spatial Alignment
• Angular Triplet Loss-based Camera Network for ReID
• Improved Res2Net model for Person re-identification
• Unsupervised Vehicle Re-identification with Progressive Adaptation
• Relation Network for Person Re-identification
• Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
• Omni-directional Feature Learning for Person Re-identification
• Attribute-Aware Attention Model for Fine-grained Representation Learning
• PGGANet: Pose Guided Graph Attention Network for Person Re-identification
• Person image generation with semantic attention network for person re-identification
• Operator-in-the-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification
• STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification
• Cluster-level Feature Alignment for Person Re-identification
• Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
• Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification
• Joint Discriminative and Metric Embedding Learning for Person Re-Identification
• Combining Two Adversarial Attacks Against Person Re-Identification Systems
• SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
• Attention Driven Person Re-identification
• Pose-Driven Deep Models for Person Re-Identification
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
• MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification
• Cross Domain Knowledge Transfer for Unsupervised Vehicle Re-identification
• Sparse Label Smoothing Regularization for Person Re-Identification
• Deep Person Re-Identification with Improved Embedding and Efficient Training
• Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
• Person Re-Identification via Active Hard Sample Mining
• Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting
• Person Re-identification with Adversarial Triplet Embedding
• Efficient Pipelines for Vision-Based Context Sensing
• Cross-Resolution Person Re-identification with Deep Antithetical Learning
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
• Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification
• Temporal Continuity Based Unsupervised Learning for Person Re-Identification
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
• FTN: Foreground-Guided Texture-Focused Person Re-Identification
• Single Camera Training for Person Re-identification
• FlipReID: Closing the Gap between Training and Inference in Person Re-Identification
• advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns