mlsanityData to 7 Oct 2026

Deep metric learning using Triplet network

arXiv 1412.6622 ↗First posted 20 Dec 2014cs.LG cs.CV stat.MLcited by 421

Not on the map. Why?

Abstract (arXiv)

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.

Key facts. Cited by 421 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 112; 2022: 98; 2023: 86; 2024: 49; 2025: 48; 2026: 28.

421 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  3. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  4. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  5. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  6. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  7. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  8. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  9. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 92
  10. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 91
  11. 2021CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representationscited by 72
  12. 2022SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellitecited by 61
38 more
  1. 2021High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learningcited by 54
  2. 2023MolFM: A Multimodal Molecular Foundation Modelcited by 50
  3. 2023First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learningcited by 46
  4. 2022Voice-Face Homogeneity Tells Deepfakecited by 44
  5. 2022LocVTP: Video-Text Pre-training for Temporal Localizationcited by 44
  6. 2022Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisationcited by 43
  7. 2021Visual Goal-Step Inference using wikiHowcited by 42
  8. 2021FEAR: Fast, Efficient, Accurate and Robust Visual Trackercited by 38
  9. 2023PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Modelscited by 36
  10. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  11. 2022Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrievalcited by 33
  12. 2023DeepGate2: Functionality-Aware Circuit Representation Learningcited by 33
  13. 2022Learning Sound Localization Better From Semantically Similar Samplescited by 32
  14. 2022AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shiftcited by 32
  15. 2023Sound Source Localization is All about Cross-Modal Alignmentcited by 30
  16. 2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
  17. 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
  18. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  19. 2022Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessmentcited by 25
  20. 2021Regular Polytope Networkscited by 24
  21. 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representationscited by 24
  22. 2021End2End Occluded Face Recognition by Masking Corrupted Featurescited by 24
  23. 2021Robust Representation Learning via Perceptual Similarity Metricscited by 23
  24. 2021Semi-TCL: Semi-Supervised Track Contrastive Representation Learningcited by 23
  25. 2021Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detectioncited by 23
  26. 2022LASER: LAtent SpacE Rendering for 2D Visual Localizationcited by 23
  27. 2021Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tagscited by 22
  28. 2021DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learningcited by 20
  29. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  30. 2022Graph Neural Network for Cell Tracking in Microscopy Videoscited by 19
  31. 2021Simplicial Complex Representation Learningcited by 17
  32. 2021Contrastive Learning for Sports Video: Unsupervised Player Classificationcited by 17
  33. 2021Neural Distance Embeddings for Biological Sequencescited by 17
  34. 2021Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attackscited by 16
  35. 2022Distributed Deep Joint Source-Channel Coding over a Multiple Access Channelcited by 16
  36. 2024PetFace: A Large-Scale Dataset and Benchmark for Animal Identificationcited by 16
  37. 2022On the Learning and Learnability of Quasimetricscited by 15
  38. 2022Action-based Contrastive Learning for Trajectory Predictioncited by 15

50 most cited of 421 All 421 (JSON)