Metric Learning Papers

Survey

• Deep Metric Learning: A Survey [paper]

• A Survey on Metric Learning for Feature Vectors and Structured Data [paper]

• A Metric Learning Reality Check (ECCV 2020) [paper]

• A Tutorial on Distance Metric Learning: Mathematical Foundations, Algorithms and Software [paper]

• A Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses (ECCV 2020) [paper]

Papers

Updating...

2023

• HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization (CVPR) [paper]

• Deep Metric Learning with Adaptively Composite Dynamic Constraints (TPAMI) [paper]

• Generative Metric Learning for Adversarially Robust Open-world Person Re-Identification (TOMM) [paper]

• Distance and Direction Based Deep Discriminant Metric Learning for Kinship Verification (TOMM) [paper]

2022

• Enhancing Adversarial Robustness for Deep Metric Learning (CVPR) [paper]

• Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification (CVPR) [paper]

• Self-Taught Metric Learning without Labels (CVPR) [paper]

• Integrating Language Guidance into Vision-based Deep Metric Learning (CVPR) [paper]

• Non-isotropy Regularization for Proxy-based Deep Metric Learning (CVPR) [paper]

• Hyperbolic Vision Transformers: Combining Improvements in Metric Learning (CVPR) [paper]

• Weakly-supervised Metric Learning with Cross-Module Communications for the Classification of Anterior Chamber Angle Images (CVPR)

• Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning (CVPR) [code]

• It Takes Two to Tango: Mixup for Deep Metric Learning (ICLR) [paper]

• Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning (ICLR) [paper]

2021

• Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales (CVPR) [paper] [code]

• Embedding Transfer with Label Relaxation for Improved Metric Learning (CVPR) [paper]

• Noise-resistant Deep Metric Learning with Ranking-based Instance Selection (CVPR) [paper] [code]

• Unsupervised Hyperbolic Metric Learning] (CVPR) [[paper]

• Deep Compositional Metric Learning (CVPR) [paper] [code]

• SLADE: A Self-Training Framework for Distance Metric Learning (CVPR) [paper]

• Asymmetric Metric Learning for Knowledge Transfer (CVPR) [paper] [code]

• Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning (CVPR) [paper]

• Discrimination-Aware Mechanism for Fine-Grained Representation Learning (CVPR) [paper]

• Deep Relational Metric Learning (ICCV) [paper] [code]

• Towards Interpretable Deep Metric Learning with Structural Matching (ICCV) [paper] [code]

• Learning with Memory-based Virtual Classes for Deep Metric Learning (ICCV) [paper]

• Do Different Deep Metric Learning Losses Lead to Similar Learned Features? (ICCV) [paper]

• Improving Deep Metric Learning by Divide and Conquer (PAMI) [paper]

• Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning (AAAI) [paper]

• Deep Metric Learning with Self-Supervised Ranking (AAAI) [paper]

2020

• Proxy Anchor Loss for Deep Metric Learning (CVPR) [paper]

• Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning (CVPR) [paper]

• Circle Loss: A Unified Perspective of Pair Similarity Optimization (CVPR) [paper]

• Moving in the Right Direction: A Regularization for Deep Metric Learning (CVPR) [paper]

• Cross-Batch Memory for Embedding Learning (CVPR Oral) [paper]

• Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies (NIPS) [paper]

• Provably Robust Metric Learning (NIPS) [paper]

• Deep Metric Learning with Spherical Embedding (NIPS) [paper]

• Distance Metric Learning with Joint Representation Diversification (ICML) [paper]

• Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (ICML) [paper]

• Symmetrical Synthesis for Deep Metric Learning (AAAI) [paper]

• Online Metric Learning for Multi-Label Classification (AAAI) [paper]

• Unsupervised Metric Learning with Synthetic Examples (AAAI) [paper]

• Compressed Self-Attention for Deep Metric Learning (AAAI) [paper]

• Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss (ECCV) [paper]

• The Group Loss for Deep Metric Learning (ECCV) [paper]

• DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning (ECCV) [paper]

• Deep Adversarial Metric Learning (TIP) [paper]

2019

• Divide and Conquer the Embedding Space for Metric Learning (CVPR) [paper]

• Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning (CVPR) [paper]

• Hardness-Aware Deep Metric Learning (CVPR Oral) [paper]

• Deep Metric Learning to Rank (CVPR) [paper]

• Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning (CVPR) [paper]

• ArcFace: Additive Angular Margin Loss for Deep Face Recognition (CVPR) [paper]

• A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning (CVPR) [paper]

• Deep Metric Learning Beyond Binary Supervision (CVPR Oral) [paper]

• Stochastic Class-based Hard Example Mining for Deep Metric Learning (CVPR) [paper]

• Deep Asymmetric Metric Learning via Rich Relationship Mining (CVPR) [paper]

• Learning Metrics from Teachers: Compact Networks for Image Embedding (CVPR) [paper] [code]

• Ranked List Loss for Deep Metric Learning (PAMI) [paper]

• SoftTriple Loss: Deep Metric Learning Without Triplet Sampling (ICCV) [paper]

• MIC: Mining Interclass Characteristics for Improved Metric Learning (ICCV) [paper]

• Deep Metric Learning with Tuplet Margin Loss (ICCV) [paper]

• Deep Meta Metric Learning (ICCV) [paper]

• Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings (ICCV) [paper]

• Classification is a Strong Baseline for Deep Metric Learning (BMVC) [paper]

2018

• Mining on Manifolds: Metric Learning Without Labels (CVPR) [paper]

• CosFace: Large Margin Cosine Loss for Deep Face Recognition (CVPR) [paper]

• Large-Scale Distance Metric Learning with Uncertainty (CVPR) [paper]

• Attention-based Ensemble for Deep Metric Learning (ECCV) [paper]

• Deep Metric Learning with Hierarchical Triplet Loss (ECCV) [paper]

• Hard-Aware Point-to-Set Deep Metric for Person Re-identification (ECCV) [paper]

• Deep Variational Metric Learning (ECCV) [paper]

• Deep Randomized Ensembles for Metric Learning (ECCV) [paper]

• Learning Deep Disentangled Embeddings With the F-Statistic Loss (NIPS) [paper]

2017

• SphereFace: Deep Hypersphere Embedding for Face Recognition (CVPR) [paper]

• Beyond triplet loss: a deep quadruplet network for person re-identification (CVPR) [paper]

• Deep Metric Learning via Facility Location (CVPR) [paper]

• Hard-Aware Deeply Cascaded Embedding (ICCV) [paper]

• No Fuss Distance Metric Learning using Proxies (ICCV) [paper]

• BIER - Boosting Independent Embeddings Robustly (ICCV Oral) [paper]

• Deep Metric Learning with Angular Loss (ICCV) [paper]

• Sampling Matters in Deep Embedding Learning (ICCV) [paper]

2016

• Deep Metric Learning via Lifted Structured Feature Embedding (CVPR) [paper]

• Improved Deep Metric Learning with Multi-class N-pair Loss Objective (NIPS) [paper]

• Learning Deep Embeddings with Histogram Loss (NIPS) [paper]

Earlier

• FaceNet: A Unified Embedding for Face Recognition and Clustering (CVPR 2015) [paper]

• Deep Metric Learning for Practical Person Re-Identification (ICPR) [paper]

• Deep metric learning using triplet network (SIMBAD 2015) [paper]

• Dimensionality Reduction by Learning an Invariant Mapping (CVPR 2006) [paper]

• Distance Metric Learning for Large Margin Nearest Neighbor Classification (NIPS 2006) [paper]

• Neighbourhood Components Analysis (NIPS 2005) [paper]