In Defense of the Triplet Loss for Person Re-Identification

Abstract

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.

Lucas Beyer and Alexander Hermans contributed equally. Updates: Minor fixes, new SOTA comparisons, add CUHK03 results

References in corpus (6)

• ADADELTA: An Adaptive Learning Rate Method
• Person Re-identification: Past, Present and Future
• Improving Person Re-identification by Attribute and Identity Learning
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Transfer Learning for Person Re-identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification

Cited by in corpus (493)

• VoxCeleb2: Deep Speaker Recognition
• A Survey on Deep Semi-supervised Learning
• Contrastive Representation Learning: A Framework and Review
• Random Erasing Data Augmentation
• Deep Learning in Video Multi-Object Tracking: A Survey
• Pedestrian Alignment Network for Large-scale Person Re-identification
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
• MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
• Body Part-Based Representation Learning for Occluded Person Re-Identification
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
• Adaptive Exploration for Unsupervised Person Re-Identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Parameter-Efficient Transfer Learning for NLP
• GSV-Cities: Toward Appropriate Supervised Visual Place Recognition
• Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Omni-Scale Feature Learning for Person Re-Identification
• Revisiting Temporal Modeling for Video-based Person ReID
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
• Second-order Non-local Attention Networks for Person Re-identification
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• Perspectives on individual animal identification from biology and computer vision
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• Deep Generalized Max Pooling
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• Deep Attention Aware Feature Learning for Person Re-Identification
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On 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
• Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
• Deep Long-Tailed Learning: A Survey
• Parameter-Efficient Person Re-identification in the 3D Space
• Lightweight Multi-Branch Network for Person Re-Identification
• Discriminative Feature Learning with Foreground Attention for Person Re-Identification
• Revisiting Self-Supervised Visual Representation Learning
• Learning to Disentangle Scenes for Person Re-identification
• ABD-Net: Attentive but Diverse Person Re-Identification
• Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
• Deep Joint Source-Channel Coding for Wireless Image Retrieval
• Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
• Unsupervised Person Re-identification by Soft Multilabel Learning
• TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
• Horizontal Pyramid Matching for Person Re-identification
• Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification
• RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
• Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs
• Cluster Contrast for Unsupervised Person Re-Identification
• Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
• Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning
• Learning Generalized Spoof Cues for Face Anti-spoofing
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Group Re-Identification with Multi-grained Matching and Integration
• Learning Efficient Representations for Keyword Spotting with Triplet Loss
• Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
• Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
• Modality-Agnostic Attention Fusion for visual search with text feedback
• MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity
• GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
• Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
• A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
• Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
• Combination of Multiple Global Descriptors for Image Retrieval
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Whitening for Self-Supervised Representation Learning
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Relation-Aware Global Attention for Person Re-identification
• Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
• Domain Adaptive Person Re-Identification via Coupling Optimization
• Learning to Adapt Invariance in Memory for Person Re-identification
• EANet: Enhancing Alignment for Cross-Domain Person Re-identification
• Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification
• Camera Style Adaptation for Person Re-identification
• PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
• Person Re-Identification by Semantic Region Representation and Topology Constraint
• Simulating Content Consistent Vehicle Datasets with Attribute Descent
• Learning Shape Representations for Clothing Variations in Person Re-Identification
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
• Adaptive neighborhood Metric learning
• Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification
• AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
• The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
• Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
• Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
• Spatiotemporal Transformer for Video-based Person Re-identification
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• ACNet: Approaching-and-Centralizing Network for Zero-Shot Sketch-Based Image Retrieval
• Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search
• Convolutional Embedding for Edit Distance
• Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
• TDIOT: Target-driven Inference for Deep Video Object Tracking
• Deep Association Learning for Unsupervised Video Person Re-identification
• Self-supervised Multi-view Person Association and Its Applications
• Sampling Agnostic Feature Representation for Long-Term Person Re-identification
• Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
• Keypoint Promptable Re-Identification
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
• Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering
• AANet: Attribute Attention Network for Person Re-Identifications
• Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
• CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
• Batch DropBlock Network for Person Re-identification and Beyond
• Deep Group-shuffling Random Walk for Person Re-identification
• Cross-modality Person re-identification with Shared-Specific Feature Transfer
• DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
• RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
• Supervised Transfer Learning at Scale for Medical Imaging
• Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding
• Learning Data Association for Multi-Object Tracking using Only Coordinates
• VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera
• DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
• Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
• Style Normalization and Restitution for Generalizable Person Re-identification
• MOPT: Multi-Object Panoptic Tracking
• Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Part-Guided Attention Learning for Vehicle Instance Retrieval
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
• Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
• HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
• Quasi-Dense Similarity Learning for Multiple Object Tracking
• Augmented Hard Example Mining for Generalizable Person Re-Identification
• Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
• Densely Semantically Aligned Person Re-Identification
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
• Contrastive Learning for Compact Single Image Dehazing
• A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
• VRSTC: Occlusion-Free Video Person Re-Identification
• Spatial and Temporal Mutual Promotion for Video-based Person Re-identification
• Large Margin Softmax Loss for Speaker Verification
• Sequential convolutional network for behavioral pattern extraction in gait recognition
• Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss
• Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation
• Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
• Recurrent Embedding Aggregation Network for Video Face Recognition
• Generalized Inter-class Loss for Gait Recognition
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
• Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition
• End-to-End Learning Deep CRF models for Multi-Object Tracking
• Self-training with progressive augmentation for unsupervised cross-domain person re-identification
• Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
• RetinaTrack: Online Single Stage Joint Detection and Tracking
• Vehicle Re-identification with Viewpoint-aware Metric Learning
• Exchangeable deep neural networks for set-to-set matching and learning
• Learning Tversky Similarity
• Unsupervised Few-shot Learning via Self-supervised Training
• Dissecting Person Re-identification from the Viewpoint of Viewpoint
• Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification
• Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
• CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
• Vehicle Re-identification in Aerial Imagery: Dataset and Approach
• GiT: Graph Interactive Transformer for Vehicle Re-identification
• HAT: Hierarchical Aggregation Transformers for Person Re-identification
• Rethinking Channel Dimensions for Efficient Model Design
• Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
• Octuplet Loss: Make Face Recognition Robust to Image Resolution
• Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
• A heterogeneous branch and multi-level classification network for person re-identification
• View Confusion Feature Learning for Person Re-identification
• Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images
• Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
• HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
• ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
• Learning to rank music tracks using triplet loss
• Deep Learning for Face Anti-Spoofing: A Survey
• Unsupervised Deep Metric Learning via Auxiliary Rotation Loss
• Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
• Generalizable Person Re-identification with Relevance-aware Mixture of Experts
• Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
• VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
• Improving Person Re-identification with Iterative Impression Aggregation
• Real-world Person Re-Identification via Degradation Invariance Learning
• TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields
• Unsupervised clothing change adaptive person ReID
• Hetero-Center Loss for Cross-Modality Person Re-Identification
• Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
• Multi-task Batch Reinforcement Learning with Metric Learning
• Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
• Estimating and abstracting the 3D structure of bones using neural networks on X-ray (2D) images
• PhishGAN: Data Augmentation and Identification of Homoglpyh Attacks
• Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples
• Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video
• It Takes Two to Tango: Mixup for Deep Metric Learning
• Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
• Adversarial Metric Attack and Defense for Person Re-identification
• STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
• DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
• RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• Neural Fuzzy Extractors: A Secure Way to Use Artificial Neural Networks for Biometric User Authentication
• Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism
• University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
• Face Detection with Feature Pyramids and Landmarks
• End-to-end Person Search Sequentially Trained on Aggregated Dataset
• Meta Batch-Instance Normalization for Generalizable Person Re-Identification
• Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
• A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification
• Camera-aware Proxies for Unsupervised Person Re-Identification
• Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
• DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
• Real-time Person Re-identification at the Edge: A Mixed Precision Approach
• Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
• Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
• A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification
• Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification
• YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID
• Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory
• Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
• Improved Embeddings with Easy Positive Triplet Mining
• Cerberus: Attribute-based person re-identification using semantic IDs
• Discriminative Pedestrian Features and Gated Channel Attention for Clothes-Changing Person Re-Identification
• Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
• ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
• GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
• An Identity-Preserved Framework for Human Motion Transfer
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking
• Grafted network for person re-identification
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations
• Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification
• Temporal Knowledge Propagation for Image-to-Video Person Re-identification
• Unity Style Transfer for Person Re-Identification
• Deep Divergence Learning
• Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
• End-to-End Deep Kronecker-Product Matching for Person Re-identification
• Adaptive L2 Regularization in Person Re-Identification
• Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?
• Multi-Scale Body-Part Mask Guided Attention for Person Re-identification
• Going Deeper into Semi-supervised Person Re-identification
• Continual Representation Learning for Biometric Identification
• SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification
• A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification
• Performance Comparison for Scientific Computations on the Edge via Relative Performance
• Weighted Bilinear Coding over Salient Body Parts for Person Re-identification
• Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
• Pedestrian re-identification based on Tree branch network with local and global learning
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
• Challenge report: Recognizing Families In the Wild Data Challenge
• Multi-Domain Learning and Identity Mining for Vehicle Re-Identification
• Robust Partial Matching for Person Search in the Wild
• Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification
• UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
• Unsupervised Pre-training for Person Re-identification
• Automatic coding of students' writing via Contrastive Representation Learning in the Wasserstein space
• AI based Algorithms of Path Planning, Navigation and Control for Mobile Ground Robots and UAVs
• Spatio-Temporal Representation Factorization for Video-based Person Re-Identification
• SiamMOT: Siamese Multi-Object Tracking
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• SemHARQ: Semantic-Aware Hybrid Automatic Repeat Request for Multi-Task Semantic Communications
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
• Rethinking Person Re-Identification via Semantic-Based Pretraining
• Hybrid-Attention Guided Network with Multiple Resolution Features for Person Re-Identification
• Learning Longterm Representations for Person Re-Identification Using Radio Signals
• End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
• Towards Backward-Compatible Representation Learning
• You Are Here: Geolocation by Embedding Maps and Images
• GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
• Ranked List Loss for Deep Metric Learning
• Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention
• Deep Similarity Metric Learning for Real-Time Pedestrian Tracking
• Collaborative Attention Network for Person Re-identification
• Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval
• Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification
• RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss
• Fashion-IQ 2020 Challenge 2nd Place Team's Solution
• ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
• A Structured Model For Action Detection
• Vehicle Re-ID for Surround-view Camera System
• Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
• Discriminability Distillation in Group Representation Learning
• Bag of Tricks and A Strong baseline for Image Copy Detection
• Towards Discriminative Representation Learning for Unsupervised Person Re-identification
• Hard negative examples are hard, but useful
• Re-ID Driven Localization Refinement for Person Search
• Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification
• Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
• View-Invariant Probabilistic Embedding for Human Pose
• Leveraging Virtual and Real Person for Unsupervised Person Re-identification
• Triplet Distillation for Deep Face Recognition
• Cooperative Cross-Stream Network for Discriminative Action Representation
• ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
• Rethinking Sampling Strategies for Unsupervised Person Re-identification
• Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification
• VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning
• Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
• Angular Triplet Loss-based Camera Network for ReID
• Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset
• Stronger Baseline for Person Re-Identification
• Multi-modal data generation with a deep metric variational autoencoder
• Visualizing How Embeddings Generalize
• PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation
• Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distance
• A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
• Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
• Attribute analysis with synthetic dataset for person re-identification
• Branch-Cooperative OSNet for Person Re-Identification
• Searching for Apparel Products from Images in the Wild
• Picture-to-Amount (PITA): Predicting Relative Ingredient Amounts from Food Images
• Integrating Coarse Granularity Part-level Features with Supervised Global-level Features for Person Re-identification
• Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
• Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
• Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models
• Support Neighbor Loss for Person Re-Identification
• Triplet Contrastive Learning for Brain Tumor Classification
• Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning
• In Defense of the Classification Loss for Person Re-Identification
• Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
• LeRoP: A Learning-Based Modular Robot Photography Framework
• Relation Network for Person Re-identification
• When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
• Supervised Representation Learning towards Generalizable Assembly State Recognition
• Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
• Learnable Adaptive Cosine Estimator (LACE) for Image Classification
• The General Pair-based Weighting Loss for Deep Metric Learning
• MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking
• Joint Discriminative and Metric Embedding Learning for Person Re-Identification
• Domain Camera Adaptation and Collaborative Multiple Feature Clustering for Unsupervised Person Re-ID
• Anchor-Free Person Search
• HPILN: A feature learning framework for cross-modality person re-identification
• ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification
• Practical Cross-modal Manifold Alignment for Grounded Language
• Intra-clip Aggregation for Video Person Re-identification
• Learning A Unified Template for Gait Recognition
• Bag of Negatives for Siamese Architectures
• Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification
• Data-Efficient Graph Embedding Learning for PCB Component Detection
• Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework
• Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
• MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks
• Combining Two Adversarial Attacks Against Person Re-Identification Systems
• Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation
• A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
• Visual Task Progress Estimation with Appearance Invariant Embeddings for Robot Control and Planning
• Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
• Go with the Flow: Perception-refined Physics Simulation
• Concentrated Multi-Grained Multi-Attention Network for Video Based Person Re-Identification
• D${}^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
• Cluster-level Feature Alignment for Person Re-identification
• Deep Ranking with Adaptive Margin Triplet Loss
• Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
• Acceleration of Large Margin Metric Learning for Nearest Neighbor Classification Using Triplet Mining and Stratified Sampling
• Neural Signatures for Licence Plate Re-identification
• Incremental Learning in Person Re-Identification
• Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering
• Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
• One for More: Selecting Generalizable Samples for Generalizable ReID Model
• Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus Images
• Learning Condition Invariant Features for Retrieval-Based Localization from 1M Images
• Deep Multi-Index Hashing for Person Re-Identification
• Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem
• STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification
• Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification
• SeanNet: Semantic Understanding Network for Localization Under Object Dynamics
• Homocentric Hypersphere Feature Embedding for Person Re-identification
• Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
• Subtask-dominated Transfer Learning for Long-tail Person Search
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
• Applying SoftTriple Loss for Supervised Language Model Fine Tuning
• Video-based Person Re-identification without Bells and Whistles
• Privacy-Preserving Person Re-Identification from Temporal Sequences with Transformer and Hungarian Optimization
• TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval
• Informative Sample-Aware Proxy for Deep Metric Learning
• ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation
• Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder
• Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
• A Novel Graph-Theoretic Deep Representation Learning Method for Multi-Label Remote Sensing Image Retrieval
• DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio
• Progressive Multi-stage Feature Mix for Person Re-Identification
• Efficient Person Search: An Anchor-Free Approach
• Topic-time Heatmaps for Human-in-the-loop Topic Detection and Tracking
• Towards Robust Bisimulation Metric Learning
• Interpretable contrastive word mover's embedding
• Learning Portrait Style Representations
• Person Re-Identification using Deep Learning Networks: A Systematic Review
• Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification
• Towards Precise Intra-camera Supervised Person Re-identification
• GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set
• MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification
• Symmetrical Synthesis for Deep Metric Learning
• Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
• Progressive Learning Algorithm for Efficient Person Re-Identification
• Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification
• Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
• Sequential End-to-end Network for Efficient Person Search
• Improving Image co-segmentation via Deep Metric Learning
• Instance and Pair-Aware Dynamic Networks for Re-Identification
• Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning
• Vehicle Re-Identification Based on Complementary Features
• Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
• Interpretable Multimodal Learning for Intelligent Regulation in Online Payment Systems
• Hard-Aware Fashion Attribute Classification
• Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
• ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
• Prime-Aware Adaptive Distillation
• Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
• Distribution Context Aware Loss for Person Re-identification
• DeepHashing using TripletLoss
• Sparse Label Smoothing Regularization for Person Re-Identification
• The Sloop System for Individual Animal Identification with Deep Learning
• Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval
• Deep Hashing using Entropy Regularised Product Quantisation Network
• MassFace: an efficient implementation using triplet loss for face recognition
• Deep Person Re-Identification with Improved Embedding and Efficient Training
• GAN-based Pose-aware Regulation for Video-based Person Re-identification
• Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
• Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
• A framework with updateable joint images re-ranking for Person Re-identification
• Global-Local Dynamic Feature Alignment Network for Person Re-Identification
• Gait Identification under Surveillance Environment based on Human Skeleton
• Class Interference Regularization
• Graphs for deep learning representations
• Vector Embeddings with Subvector Permutation Invariance using a Triplet Enhanced Autoencoder
• FTN: Foreground-Guided Texture-Focused Person Re-Identification
• Set Augmented Triplet Loss for Video Person Re-Identification
• Single Camera Training for Person Re-identification
• CHD:Consecutive Horizontal Dropout for Human Gait Feature Extraction
• Dynamic Sampling for Deep Metric Learning
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
• Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services
• Neighborhood Watch: Representation Learning with Local-Margin Triplet Loss and Sampling Strategy for K-Nearest-Neighbor Image Classification
• Local-Global Associative Frame Assemble in Video Re-ID
• Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
• Learning Models for Query by Vocal Percussion: A Comparative Study
• Unified Multifaceted Feature Learning for Person Re-Identification
• Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals
• Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
• Cooperative Embeddings for Instance, Attribute and Category Retrieval
• Generalizing Neural Networks by Reflecting Deviating Data in Production
• Ranking and Classification driven Feature Learning for Person Re_identification
• VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification
• Adaptive Deep Metric Embeddings for Person Re-Identification under Occlusions
• Soccer Player Tracking in Low Quality Video
• A Technical Report for ICCV 2021 VIPriors Re-identification Challenge
• Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
• Video Surveillance for Road Traffic Monitoring
• Learning Compatible Embeddings
• On Learning Density Aware Embeddings
• Learning Incremental Triplet Margin for Person Re-identification
• Composing Text and Image for Image Retrieval - An Empirical Odyssey
• Ranking labs-of-origin for genetically engineered DNA using Metric Learning
• U-vectors: Generating clusterable speaker embedding from unlabeled data
• Hotels-50K: A Global Hotel Recognition Dataset
• Harnessing Geometric Constraints from Emotion Labels to improve Face Verification
• Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval
• Domain adaptation for person re-identification on new unlabeled data using AlignedReID++
• Image-Based Geo-Localization Using Satellite Imagery
• ExeChecker: Where Did I Go Wrong?
• Learning Resolution-Invariant Deep Representations for Person Re-Identification
• Unique Faces Recognition in Videos
• Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
• Learning Quintuplet Loss for Large-scale Visual Geo-Localization
• TCDesc: Learning Topology Consistent Descriptors
• Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification
• Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
• Person Re-identification with Bias-controlled Adversarial Training
• SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence Embedding
• E-Sports Talent Scouting Based on Multimodal Twitch Stream Data
• PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
• Triplet Loss for Knowledge Distillation
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
• Unveiling the Potential: Harnessing Deep Metric Learning to Circumvent Video Streaming Encryption
• Cross-modal Image Retrieval with Deep Mutual Information Maximization
• SVMax: A Feature Embedding Regularizer
• Person Re-identification based on Robust Features in Open-world
• Person Re-identification with Adversarial Triplet Embedding