mlsanityData to 7 Oct 2026

DeepID3: Face Recognition with Very Deep Neural Networks

arXiv 1502.00873 ↗First posted 3 Feb 2015cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

The state-of-the-art of face recognition has been significantly advanced by the emergence of deep learning. Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity. This motivates us to investigate their effectiveness on face recognition. This paper proposes two very deep neural network architectures, referred to as DeepID3, for face recognition. These two architectures are rebuilt from stacked convolution and inception layers proposed in VGG net and GoogLeNet to make them suitable to face recognition. Joint face identification-verification supervisory signals are added to both intermediate and final feature extraction layers during training. An ensemble of the proposed two architectures achieves 99.53% LFW face verification accuracy and 96.0% LFW rank-1 face identification accuracy, respectively. A further discussion of LFW face verification result is given in the end.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 13; 2023: 6; 2024: 6; 2025: 7; 2026: 1.

62 papers.

Sort:

By area:

  1. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  2. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  3. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  4. 2022WebFace260M: A Benchmark for Million-Scale Deep Face Recognitioncited by 41
  5. 2021Learning Compatible Embeddingscited by 37
  6. 2021Face.evoLVe: A High-Performance Face Recognition Librarycited by 26
  7. 2021Multi-granularity Textual Adversarial Attack with Behavior Cloningcited by 21
  8. 2021Textual Backdoor Attacks Can Be More Harmful via Two Simple Trickscited by 17
  9. 2021Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networkscited by 13
  10. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  11. 2021Deep Rival Penalized Competitive Learning for Low-resolution Face Recognitioncited by 10
  12. 2022Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimationcited by 9
38 more
  1. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  2. 2021TAD: Trigger Approximation based Black-box Trojan Detection for AIcited by 8
  3. 2021Recent Advances in Deep Learning Techniques for Face Recognitioncited by 5
  4. 2021Attribute-Based Deep Periocular Recognition: Leveraging Soft Biometrics to Improve Periocular Recognitioncited by 5
  5. 2022Exploring the Intersection between Neural Architecture Search and Continual Learningcited by 4
  6. 2024A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmissioncited by 4
  7. 2021Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Mapscited by 3
  8. 2021An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future workscited by 3
  9. 2021A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasetscited by 3
  10. 2021Automatic Semantic Segmentation of the Lumbar Spine: Clinical Applicability in a Multi-parametric and Multi-centre Study on Magnetic Resonance Imagescited by 3
  11. 2021PAM: Pose Attention Module for Pose-Invariant Face Recognitioncited by 3
  12. 2022Deep face recognition with clustering based domain adaptationcited by 3
  13. 2023Open-set Face Recognition using Ensembles trained on Clustered Datacited by 3
  14. 2024A Multi-task Adversarial Attack Against Face Authenticationcited by 3
  15. 2025TrainVerify: Equivalence-Based Verification for Distributed LLM Trainingcited by 3
  16. 2021Inter-class Discrepancy Alignment for Face Recognitioncited by 2
  17. 2021Open-set Face Recognition for Small Galleries Using Siamese Networkscited by 2
  18. 2021Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistencycited by 2
  19. 2022OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representationcited by 2
  20. 2023A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximationcited by 2
  21. 2023Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detectioncited by 2
  22. 2025Object Recognition Datasets and Challenges: A Reviewcited by 2
  23. 20213D Face Recognition: A Surveycited by 1
  24. 2021CrossedWires: A Dataset of Syntactically Equivalent but Semantically Disparate Deep Learning Modelscited by 1
  25. 2021SafeAccess+: An Intelligent System to make Smart Home Safer and Americans with Disability Act Compliantcited by 1
  26. 2022Pre-Trained Language Transformers are Universal Image Classifierscited by 1
  27. 2022An Adaptive Black-box Backdoor Detection Method for Deep Neural Networkscited by 1
  28. 2022Analysis of face detection, face landmarking, and face recognition performance with masked face imagescited by 1
  29. 2022Confidence-Calibrated Face and Kinship Verificationcited by 1
  30. 2023Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundarycited by 1
  31. 2023Rethinking the Domain Gap in Near-infrared Face Recognitioncited by 1
  32. 2023Ensemble Interpretation: A Unified Method for Interpretable Machine Learningcited by 1
  33. 2024Celeb-FBI: A Benchmark Dataset on Human Full Body Images and Age, Gender, Height and Weight Estimation using Deep Learning Approachcited by 1
  34. 2025Face Identity Unlearning for Retrieval via Embedding Dispersioncited by 1
  35. 2021A Multiple Classifier Approach for Concatenate-Designed Neural Networkscited by 0
  36. 2021Face Recognition Using Sf3CNN With Higher Feature Discriminationcited by 0
  37. 2021A Logical Neural Network Structure With More Direct Mapping From Logical Relationscited by 0
  38. 2021A Study of Multimodal Person Verification Using Audio-Visual-Thermal Datacited by 0

50 most cited of 62 All 62 (JSON)