mlsanityData to 7 Oct 2026

FaceNet: A Unified Embedding for Face Recognition and Clustering

arXiv 1503.03832 ↗First posted 12 Mar 2015cs.CVcited by 2,833

Not on the map. Why?

Cited by 90 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as feature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best published result by 30% on both datasets. We also introduce the concept of harmonic embeddings, and a harmonic triplet loss, which describe different versions of face embeddings (produced by different networks) that are compatible to each other and allow for direct comparison between each other.

Key facts. Cited by 2,833 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Mar 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 616; 2022: 556; 2023: 525; 2024: 448; 2025: 429; 2026: 258.

2,833 papers.

Sort:

By area:

  1. 2023MusicLM: Generating Music From Textcited by 442
  2. 2023Universal Guidance for Diffusion Modelscited by 426
  3. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  4. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  5. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  6. 2023PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embeddingcited by 324
  7. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  8. 2021Video Transformer Networkcited by 271
  9. 2023A Cookbook of Self-Supervised Learningcited by 248
  10. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 244
  11. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  12. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 242
38 more
  1. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  2. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 239
  3. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  4. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  5. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  6. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 166
  7. 2022Towards Metrical Reconstruction of Human Facescited by 165
  8. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  9. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  10. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Modelscited by 148
  11. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  12. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  13. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  14. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  15. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  16. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  17. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  18. 2022CyCLIP: Cyclic Contrastive Language-Image Pretrainingcited by 127
  19. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  20. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  21. 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modelingcited by 112
  22. 2021Are Convolutional Neural Networks or Transformers more like human vision?cited by 109
  23. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  24. 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 107
  25. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  26. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  27. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  28. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 95
  29. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  30. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  31. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  32. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  33. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  34. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
  35. 2021A Comprehensive Study on Face Recognition Biases Beyond Demographicscited by 86
  36. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  37. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  38. 2022Self-Supervised Learning for Videos: A Surveycited by 85

50 most cited of 2,833 All 2,833 (JSON)