FaceNet: A unified embedding for face recognition and clustering
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Despite significant recent advances in the field of face recognition [10, 14, 15, 17], 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 offace 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 asfeature 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-artface recognition performance using only 128-bytes perface. 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 [15] by 30% on both datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Current face recognition systems [8,24,43], already reach very high levels of accuracy in public non-forensic benchmarks, and it is expected that in the coming years they will keep improving.”
From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [43]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“An increasing number of UDA techniques have been applied in HAR; however, most of them work between domains that share the same feature space; for example, transferring the learn models between users [44] or between sensor wearing positions [32].”
From ContrasGAN: Unsupervised domain adaptation in Human Activity Recognition via adversarial and contrastive learning (2021) · cites this paper as [32]
Experimental — accuracy not yet measuredIn the citing paper
“To address this issue, a representation learning method using triplet loss is proposed to directly learn discriminative and compact face embedding [99].”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [99]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 8×
“We would like to thank Johannes Steffens for his discussions and great insights on face recognition and Christian Szegedy for providing new network architectures like [16] and discussing network design choices.”
MethodResultInfluentialLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · cited 2×
“In all our experiments we train the CNN using Stochastic Gradient Descent (SGD) with standard backprop [8, 11] and AdaGrad [5].”
MethodVisualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 5×
“This table show the structure of our Zeiler&Fergus [22] based model with 1×1 convolutions inspired by [9].”
BackgroundMethodInfluentialBackpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 2×
“In all our experiments we train the CNN using Stochastic Gradient Descent (SGD) with standard backprop [8, 11] and AdaGrad [5].”
Method(2010) · Cited by 8,261
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 9×
“[17], for example, performs a complex 3D alignment.”
BackgroundMethodInfluentialBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“Choosing which triplets to use turns out to be very important for achieving good performance and, inspired by curriculum learning [1], we present a novel online negative exemplar mining strategy which ensures consistently increasing difficulty of triplets as the network trains.”
BackgroundLarge Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
Distance Metric Learning for Large Margin Nearest Neighbor Classification
Weinberger, K. Q., & Saul, L. K. (2009) · Journal of Machine Learning Research · doi:10.5555/1577069.1577078 · Cited by 4,044 · cited 4×
“D embedding using a tripletbased loss function based on LMNN [19].”
MethodInfluentialDeep Learning Face Representation by Joint Identification-Verification
Sun, Y., Wang, X., & Tang, X. (2014) · arXiv · doi:10.48550/arxiv.1406.4773 · Cited by 1,906 · cited 4×
“the one using pairs of positives and negatives, as used in [14] Eq.”
BackgroundMethodInfluential
Research works printed but not linked: 2
- huang, 2007, Labeled faces in the wild: A database for studying face recognition in unconstrained environments, Technical Report, 7
- lin, 2013, Network in network, CaRR abs/1312 4400
Cited by
Items 601–700 of 1,094
Macas, M., Wu, C., & Fuertes, W. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122223 · Cited by 210
Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization
Li, R., Yuan, Y., Zhang, W., & Yuan, Y. (2018) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12351 · Cited by 141
“And as suggested by Schroff et al. (2015), selecting those “very-hard” negatives can, in practice, lead to bad local minima early on in training.”
BackgroundMethodFace Space Representations in Deep Convolutional Neural Networks
O’Toole, A. J., Castillo, C. D., Parde, C. J., Hill, M. Q., & Chellappa, R. (2018) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2018.06.006 · Cited by 142
A survey on face data augmentation for the training of deep neural networks
Wang, X., Wang, K., & Lian, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04748-3 · Cited by 141
“The remarkable work by Facebook [1] and Google [2] demonstrated the effectiveness of large-scale datasets on obtaining high-quality trained model, and revealed that deep learning strongly relies on large and complex training sets to generalize well in unconstrained settings.”
BackgroundDeep Face Representations for Differential Morphing Attack Detection
Scherhag, U., Rathgeb, C., Merkle, J., & Busch, C. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2994750 · Cited by 152
Real-time determination of earthquake focal mechanism via deep learning
Kuang, W., Yuan, C., & Zhang, J. (2021) · Nature Communications · doi:10.1038/s41467-021-21670-x · Cited by 164
Deep Spoken Keyword Spotting: An Overview
López‐Espejo, I., Tan, Z., Hansen, J. H. L., & Jensen, J. (2021) · IEEE Access · doi:10.1109/access.2021.3139508 · Cited by 204
“The goal is to, first, multistyle train the keyword embedding extractor by means of a (CN ,2 + 1)-pair loss function extending the idea behind tuple-based losses like N -pair [178] and triplet [179] losses (the latter used both standalone [103] and combined with the”
MethodHow Image Degradations Affect Deep CNN-Based Face Recognition?
Karahan, S., Kilinc Yildirum, M., Kirtac, K., Rende, F. S., Butun, G., & Ekenel, H. K. (2016) · 2016 International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.1109/biosig.2016.7736924 · Cited by 99
“With the recent advances in deep convolutional neural networks, researchers have reached encouraging improvements in face recognition accuracy on the LFW [1] and YouTube Faces [2] datasets [3], [4], [5].”
BackgroundPalmprint and Palmvein Recognition Based on DCNN and A New Large-Scale Contactless Palmvein Dataset
Zhang, L., Cheng, Z., Shen, Y., & Wang, D. (2018) · Symmetry · doi:10.3390/sym10040078 · Cited by 143
Person Reidentification via Structural Deep Metric Learning
Yang, X., Zhou, P., & Wang, M. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2861991 · Cited by 156
Semantic Image Inpainting with Progressive Generative Networks
Zhang, H., Hu, Z., Luo, C., Zuo, W., & Wang, M. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240625 · Cited by 156
A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition
Ghazi, M. M., & Ekenel, H. K. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.20 · Cited by 102
Generative Multi-View Human Action Recognition
Wang, L., Ding, Z., Tao, Z., Liu, Y., & Fu, Y. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00631 · Cited by 158
A cell atlas foundation model for scalable search of similar human cells
Heimberg, G., Kuo, T., DePianto, D. J., Salem, O., Heigl, T., Diamant, N., Scalia, G., Biancalani, T., Turley, S. J., Rock, J. R., et al. (2025) · Nature · doi:10.1038/s41586-024-08411-y · Cited by 136
Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
Cohen, G., Sapiro, G., & Giryes, R. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01446 · Cited by 197
Convolutional neural network with margin loss for fake news detection
Goldani, M. H., Safabakhsh, R., & Momtazi, S. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102418 · Cited by 160
Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems
Xin, L., Song, W. W., Cao, Z., & Zhang, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17430 · Cited by 238
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Bae, G., Gorce, M. D. L., Baltrušaitis, T., Hewitt, C., Chen, D., Valentin, J., Cipolla, R., & Shen, J. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00352 · Cited by 223
“Google used 100M-200M images of 8M identities to train FaceNet [29], and Facebook used 500M images of 10M identities [31].”
MethodExploiting Multi-grain Ranking Constraints for Precisely Searching Visually-similar Vehicles
Yan, K., Tian, Y., Wang, Y., Zeng, W., & Huang, T. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.68 · Cited by 150
“Triplet [24, 26, 25] and quadruplet [30] are special cases of this formulation corresponding to n = 2 and n = 3 respectively.”
BackgroundMethodDamer, N., Saladie, A. M., Braun, A., & Kuijper, A. (2018) · 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2018.8698563 · Cited by 133
“OpenFace [2] is a general-purpose face recognition library based on the deep neural network (DNN) FaceNet architecture suggested in [46].”
BackgroundWhite-box fairness testing through adversarial sampling
Zhang, P., Wang, J., Sun, J., Dong, G., Wang, X., Wang, X., Dong, J. S., & Dai, T. (2020) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3377811.3380331 · Cited by 184
“Deep neural networks (DNNs) are gradually adopted in a wide range of applications, including fraud detection [9], facial recognition [22], self-driving [5], and medical diagnosis [27].”
BackgroundAugmentation Invariant and Instance Spreading Feature for Softmax Embedding
Ye, M., Shen, J., Zhang, X., Yuen, P. C., & Chang, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3013379 · Cited by 140
JWSAA: Joint weak saliency and attention aware for person re-identification
Ning, X., Gong, K., Li, W., & Zhang, L. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.05.106 · Cited by 142
Semantically Contrastive Learning for Low-Light Image Enhancement
Liang, D., Li, L., Wei, M., Yang, S., Zhang, L., Yang, W., Du, Y., & Zhou, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20046 · Cited by 178
Ensemble Distribution Distillation
Gales, M., Malinin, A., & Mlodozeniec, B. (2019) · arXiv (Cornell University) · doi:10.17863/cam.49348 · Cited by 114
Frankenstein: Learning Deep Face Representations Using Small Data
Hu, G., Peng, X., Yang, Y., Hospedales, T. M., & Verbeek, J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2756450 · Cited by 137
Learning Spread-Out Local Feature Descriptors
Zhang, X., Yu, F. X., Kumar, S., & Chang, S.-F. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.492 · Cited by 132
Multiset Feature Learning for Highly Imbalanced Data Classification
Jing, X., Zhang, X., Zhu, X., Wu, F., You, X., Gao, Y., Shan, S., & Yang, J.-Y. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2929166 · Cited by 150
Yuan, Y., Chen, W., Yang, Y., & Wang, Z. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00185 · Cited by 144
“Instead, the comparative losses [31, 7, 25, 49], which compares the distances between two sample pairs, are naturally better choices, as empirically validated by a handful of works [21, 19, 4, 40, 5].”
FPGAN: Face de-identification method with generative adversarial networks for social robots
Lin, J., Li, Y., & Yang, G. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.09.001 · Cited by 141
C 2 SLR: Consistency-enhanced Continuous Sign Language Recognition
Zuo, R., & Mak, B. K.-W. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00507 · Cited by 209
“In this work, we follow the common practice [18, 33, 41, 52] that sampling another video from the mini-batch and taking its sequential features as the negative sample.”
MethodSynthetic data for face recognition: Current state and future prospects
Boutros, F., Štruc, V., Fiérrez, J., & Damer, N. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104688 · Cited by 187
Stochastic Class-Based Hard Example Mining for Deep Metric Learning
Suh, Y., Han, B., Kim, W., & Lee, K. M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00742 · Cited by 133
“To reduce the computational overhead to identify hard examples, existing works have explored two directions: an exact search within each minibatch [20, 7, 19] and an approximate search from the whole dataset.”
BackgroundInfluentialMargin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies
Liu, W., Luo, W., Li, Z., Zhao, P., & Gao, S. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/419 · Cited by 129
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
Makino, T., Liao, H., Assael, Y., Shillingford, B., Garcia, B., Braga, O., & Siohan, O. (2019) · 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru46091.2019.9004036 · Cited by 129
Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding
Deldari, S., Smith, D. V., Xue, H., & Salim, F. D. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449903 · Cited by 136
“A number of sampling strategies have been proposed, including hard negative sampling [43], semi-hard mining [41], distance weighted”
BackgroundGraph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
Liao, S., & Shao, L. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00721 · Cited by 141
Advances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets
Kopalidis, T., Solachidis, V., Vretos, N., & Daras, P. (2024) · Information · doi:10.3390/info15030135 · Cited by 247
Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
Wang, Y., Gong, D., Zhou, Z., Ji, X., Wang, H., Li, Z., Liu, W., & Zhang, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_45 · Cited by 130
“With the evolution of deep learning, the performance of general face recognition (GFR) has been significantly improved in recent years, even higher than humans’ abilities [35,37,36,34,46,26,42].”
BackgroundPrivacy-Protective-GAN for Privacy Preserving Face De-Identification
Wu, Y., Yang, F., Xu, Y., & Ling, H. (2019) · Journal of Computer Science and Technology · doi:10.1007/s11390-019-1898-8 · Cited by 220
“Motivated by FaceNet[34], we strive for an embedding f(x) so that the squared distance among C o n v + B a tc h N o rm In p u t Concatenation In p u t S tr id e = 2 S tr id e = 2 S tr id e = 1 S tr id e = 1 Input : Conv 4x4 Conv 4x4+BatchNorm+LeakyRelu Conv 4x4+LeakyRelu Deconv 4x4+BatchNorm+50% Drop+Relu Deconv 4x4+B…”
MethodInfluentialJung, H., Park, E., & Yoo, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01241 · Cited by 169
“Deep metric learning [52, 44, 23] has been widely applied in various fields, such as face recognition [41, 18] and image ranking [51, 34, 1].”
BackgroundSelf-restrained triplet loss for accurate masked face recognition
Boutros, F., Damer, N., Kirchbuchner, F., & Kuijper, A. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108473 · Cited by 161
“The work proposed to fine-tune FaceNet model [17] using simulated masked face images to improve the recognition accuracy.”
BackgroundMethodInfluentialA Lightened CNN for Deep Face RepresentationPreprint
Wu, X., He, R., & Sun, Z. (2015) · arXiv (Cornell University) · Cited by 147
Consistent-Aware Deep Learning for Person Re-identification in a Camera Network
Lin, J., Ren, L., Lu, J., Feng, J., & Zhou, J. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.362 · Cited by 145
“Deep Learning: Deep learning has achieved great successes on various computer vision applications such as image classification [11, 15, 30, 32], object detection [7, 8, 10, 27, 28], face recognition [29, 31, 33], etc.”
BackgroundOccluded Face Recognition in the Wild by Identity-Diversity Inpainting
Ge, S., Li, C., Zhao, S., & Zeng, D. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2967754 · Cited by 148
“After that, various loss functions have been proposed for training face recognition models, such as triplet loss [4], [6], [36], center loss [5], Sphere loss [30], range loss [31], Cos Loss [32] and ring loss [33].”
BackgroundTowards Transferable Targeted Attack
Li, M., Deng, C. D., Li, T., Yan, J., Gao, X., & Huang, H. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00072 · Cited by 185
“The standard triplet loss often uses triplet input {x, x, x} for loss computation [10, 19].”
MethodA Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses
Boudiaf, M., Rony, J., Ziko, I. M., Granger, É., Pedersoli, M., Piantanida, P., & Ayed, I. B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58539-6_33 · Cited by 227
Hard Negative Examples are Hard, but Useful
Xuan, H., Stylianou, A., Liu, X., & Pless, R. B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58568-6_8 · Cited by 134
SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance
Ou, F.-Z., Chen, X., Zhang, R., Huang, Y., Li, S., Li, J., Li, Y., Cao, L., & Wang, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00758 · Cited by 192
Cai, Y., Li, X., & Li, J. (2023) · Sensors · doi:10.3390/s23052455 · Cited by 180
“It is also difficult to effectively recognize emotions when the face is occluded (wearing a mask) or from different shooting angles [39]. is also difficult to effectively recognize emotions when the face is occluded wearing a mask) or from different shooting angles [39].”
BackgroundMetric Learning with Adaptive Density DiscriminationPreprint
Rippel, O., Paluri, M., Dollár, P., & Bourdev, L. D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05939 · Cited by 237
“In this case, a ubiquitous solution is to enforce semantic similarity: examples of each class are demanded to be tightly clustered together, far from examples of other classes (for example, Schroff et al. (2015); Norouzi et al. (2012); Globerson & Roweis (2006); Chopra et al. (2005)).”
BackgroundInfluentialCompressing Convolutional Neural Networks in the Frequency Domain
Chen, W., Wilson, J., Tyree, S., Weinberger, K. Q., & Chen, Y. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939839 · Cited by 127
Bolt loosening angle detection technology using deep learning
Zhao, X., Zhang, Y., & Wang, N. (2019) · Structural Control and Health Monitoring · doi:10.1002/stc.2292 · Cited by 133
Toward Intelligent Sensing: Intermediate Deep Feature Compression
Chen, Z., Fan, K., Wang, S., Duan, L., Lin, W., & Kot, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2941660 · Cited by 168
“For instance, in the face recognition task, the deep feature of a human face is only with dimension of 4K in Facebook DeepFace [19], 128 in Google FaceNet [24], and 300 in Sense-Time DeepID3 [25].”
BackgroundLin, J., Yuan, Y., Shao, T., & Zhou, K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00593 · Cited by 160
SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
Zhong, Y., Deng, W., Hu, J., Zhao, D., Li, X., & Wen, D. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048632 · Cited by 168
Neighbor Contrastive Learning on Learnable Graph Augmentation
Shen, X., Sun, D., Pan, S., Zhou, X., & Yang, L. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26168 · Cited by 205
Adversarial Sticker: A Stealthy Attack Method in the Physical World
Wei, X., Guo, Y., & Yu, J. (2021) · arXiv · doi:10.48550/arxiv.2104.06728 · Cited by 133
“The results show that the probabilities in different models are significantly reduced, and the maximum reduction in FaceNet, SphereFace, and CosFace after attacks are 0.64, 0.65, and 0.76, respectively.”
BackgroundMethodInfluentialData augmentation for face recognition
Lv, J.-J., Shao, X., Huang, J., Zhou, X., & Zhou, X. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.12.025 · Cited by 140
BIER — Boosting Independent Embeddings Robustly
Opitz, M., Waltner, G., Possegger, H., & Bischof, H. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.555 · Cited by 138
“[35, 40, 48], and sample a mini-batch of several images, forward propagate them through the network and sample pairs or triplets in the last loss layer of the network.”
BackgroundImproving Generalization via Scalable Neighborhood Component Analysis
Wu, Z., Efros, A. A., & Yu, S. X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_42 · Cited by 163
Improving transferability of adversarial patches on face recognition with generative models
Xiao, Z., Gao, X., Fu, C., Dong, Y., Gao, W., Zhang, X., Zhou, J., & Zhu, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01167 · Cited by 132
“Deep convolutional neural networks (CNNs) have led to substantial performance improvements on many com- *Equal contributions.”
BackgroundMethodInfluentialAccelerating DETR Convergence via Semantic-Aligned Matching
Zhang, G., Luo, Z., Yu, Y., Cui, K., & Lu, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00102 · Cited by 168
MovieGraphs: Towards Understanding Human-Centric Situations from Videos
Vicol, P. A., Tapaswi, M., Castrejón, L., & Fidler, S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00895 · Cited by 189
Li, S., & Deng, W. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1131-1 · Cited by 163
“2006), triplet loss (Schroff et al. 2015) and center loss (Wen et al.”
BackgroundSecure Face Matching Using Fully Homomorphic Encryption
Boddeti, V. N. (2018) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2018.8698601 · Cited by 144
Image Generators with Conditionally-Independent Pixel Synthesis
Anokhin, I., Demochkin, K. V., Khakhulin, T., Sterkin, G., Lempitsky, V., & Korzhenkov, D. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01405 · Cited by 184
Local Similarity-Aware Deep Feature EmbeddingPreprint
Huang, C., Loy, C. C., & Tang, X. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.08904 · Cited by 168
“Deep Euclidean metric Triplet loss [27,33] Position-Dependent Deep Metric Double header hinge loss”
BackgroundInfluentialFace Attention Network: An Effective Face Detector for the Occluded Faces
Wang, J., Yuan, Y., & Yu, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07246 · Cited by 131
“face landmark [31, 40] and face recognition [24, 27, 41].”
Deep learning for source camera identification on mobile devices
Freire-Obregón, D., Narducci, F., Barra, S., & Castrillón-Santana, M. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.01.005 · Cited by 149
Duplex Metric Learning for Image Set Classification
Cheng, G., Zhou, P., & Han, J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2760512 · Cited by 130
A Modulation Module for Multi-task Learning with Applications in Image Retrieval
Zhao, X., Li, H., Shen, X., Liang, X., & Wu, Y. N. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01246-5_25 · Cited by 184
Pothole detection using location-aware convolutional neural networks
Chen, H., Yao, M., & Gu, Q. (2020) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-020-01078-7 · Cited by 130
We Can Detect Your Bias: Predicting the Political Ideology of News Articles
Baly, R., Da San Martino, G., Glass, J., & Nakov, P. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.404 · Cited by 125
Zhang, J., Liu, Y., Yang, H., & Cao, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i15.29617 · Cited by 253
Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identificationPreprint
Xiao, Q., Luo, H., & Zhang, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.00478 · Cited by 178
An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics
Conti, F., Schilling, R., Schiavone, P. D., Pullini, A., Rossi, D., Gürkaynak, F. K., Muehlberghuber, M., Gautschi, M., Loi, I., Haugou, G., et al. (2017) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2017.2698019 · Cited by 147
UniformFace: Learning Deep Equidistributed Representation for Face Recognition
Duan, Y., Lu, J., & Zhou, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00353 · Cited by 148
Contrastive Code Representation Learning
Jain, P., Jain, A., Zhang, T., Abbeel, P., Gonzalez, J., & Stoica, I. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.482 · Cited by 129
Contrastive Code Representation Learning
Jain, P., Jain, A., Zhang, T., Abbeel, P., Gonzalez, J. E., & Stoica, I. (2020) · arXiv · doi:10.48550/arxiv.2007.04973 · Cited by 129
Local Deep Neural Networks for gender recognition
Mansanet, J., Albiol, A., & Paredes, R. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.11.015 · Cited by 129
“…DCNNs models has shown great performance in computer vision tasks by learning from small regions in the visual field, (Krizhevsky et al. (2012); Simonyan and Zisserman (2014)) and have been successfully used for face recognition (Taigman et al. (2014); Sun et al. (2014); Schroff et al. (2015)).”
MethodA PID Controller Approach for Stochastic Optimization of Deep Networks
An, W., Wang, H., Sun, Q., Xu, J., Dai, Q., & Zhang, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00889 · Cited by 129
Vehicle Re-identification: an Efficient Baseline Using Triplet Embedding
Kuma, R., Weill, E., Aghdasi, F., & Sriram, P. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852059 · Cited by 122
Information Bottleneck Disentanglement for Identity Swapping
Gao, G., Huang, H., Fu, C., Li, Z., & He, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00341 · Cited by 123
“Previously, contrastive losses are usually used in face recognition as a max-margin approach for better separating positive from negative examples [9, 38, 46].”
BackgroundSemi-Supervised Specific Emitter Identification Method Using Metric-Adversarial Training
Fu, X. G., Peng, Y., Liu, Y., Lin, Y., Gui, G., Gacanin, H., & Adachi, F. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3240242 · Cited by 135
“[47] proposed triplet loss which was different from the triplet loss of [44] and DNN to classify ship-radiated noise.”
BackgroundFairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
Kärkkäinen, K., & Joo, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04913 · Cited by 126
“To date, numerous large scale face image datasets [22, 31, 13, 69, 37, 24, 41, 68, 15, 27, 46, 8, 39] have been proposed and fostered research and development for automated face detection [35, 21], alignment [66, 44], recognition [57, 49], generation [67, 5, 26, 58], modification [3, 32, 19], and attribute classificat…”
BackgroundAn end to end Deep Neural Network for iris segmentation in unconstrained scenarios
Bazrafkan, S., Thavalengal, S., & Corcoran, P. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.06.011 · Cited by 137
“rtificial intelligence and machine vision science. Deep learning based techniques are noted to provide state of the art results in various applications such as object detection [31], face recognition [32], driver monitoring systems [33], etc. In such deep learning based approaches, the input signal (image) is processe…”
BackgroundZhang, Y., Pan, P., Zheng, Y., Zhao, K., Zhang, Y., Ren, X., & Jin, R. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3219820 · Cited by 135
“FaceNet [15] is employed, which suggested an online strategy by associating each positive pair in the minibatch with a semi-hard negative example.”
MethodAdversarial Sticker: A Stealthy Attack Method in the Physical World
Wei, X., Guo, Y., & Yu, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3176760 · Cited by 216
“Target models : We choose three representative face recognition models, CosFace [48], SphereFace [49] and FaceNet [44], as our target models.”
MethodInfluentialHyper-sausage coverage function neuron model and learning algorithm for image classification
Ning, X., Tian, W., Feng, H., Bai, X. P., Sun, L., & Li, W. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109216 · Cited by 136
Cross-Modality Transformer With Modality Mining for Visible-Infrared Person Re-Identification
Liang, T., Jin, Y., Liu, W., & Li, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3237155 · Cited by 155
Focus: Querying Large Video Datasets with Low Latency and Low Cost
Hsieh, K., Ananthanarayanan, G., Bodík, P., Bahl, P., Philipose, M., Gibbons, P. B., & Mutlu, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.03493 · Cited by 93
Pose-invariant face recognition with homography-based normalization
Ding, C., & Tao, D. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.024 · Cited by 126
Finger vein identification using Convolutional Neural Network and supervised discrete hashing
Xie, C., & Kumar, A. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.12.001 · Cited by 135
“We incorporated triplet similarity loss function as detailed in [7] for LCNN to learn the similarity metric.”
MethodFast Training of Triplet-Based Deep Binary Embedding Networks
Zhuang, B., Lin, G., Shen, C., & Reid, I. D. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.641 · Cited by 129
“Despite using only publicly available training data and one single network, the performance of this model is competitive with state-of-the-art [25, 29, 30, 37].”
BackgroundMethodInfluentialTowards Learning a Universal Non-Semantic Representation of Speech
Shor, J., Jansen, A., Maor, R., Lang, O., Tuval, O., Quitry, F. D. C., Tagliasacchi, M., Shavitt, I., Emanuel, D., & Haviv, Y. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-1242 · Cited by 123
“We use the now-standard within-batch semi-hard negative mining technique [29].”
MethodRethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications
Brattoli, B., Tighe, J., Zhdanov, F., Perona, P., & Chalupka, K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00467 · Cited by 174
“This approach is called zero-shot learning (ZSL) [29, 34] and it is quite successful in the image domain [41, 42, 44, 45, 47, 56].”
BackgroundAn Intrusion Detection Method Using Few-Shot Learning
Yu, Y., & Bian, N. (2020) · IEEE Access · doi:10.1109/access.2020.2980136 · Cited by 147
“The triplet loss [16] was proposed to increase the Euclidean margin for different classes of feature embedding.”
BackgroundText-based Person Search via Attribute-aided Matching
Aggarwal, S., Babu, R. V., & Chakraborty, A. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093640 · Cited by 141
“Triplet loss [17, 25] is popularly used to learn a discriminative alignment of features.”
BackgroundMethodExploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-Identification
Shen, F., Zhu, J., Zhu, X., Xie, Y. F., & Huang, J. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3086142 · Cited by 146
“, [11–13, 18, 30]) show promising performance by combining softmax [47, 48] and triplet loss [11, 49] functions.”
Background
Metadata
- Authors
- Schroff, F., Kalenichenko, D., & Philbin, J.
- Affiliations
- Google (United States) (US)
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 815-823
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2096733369
- Semantic Scholar
- 5aa26299435bdf7db874ef1640a6c3b5a4a2c394
- Cited by
- 15,267
- References
- 22
- Citations by year
- 2026: 846 · 2025: 1556 · 2024: 1590 · 2023: 1823 · 2022: 1872 · 2021: 2113 · 2020: 1902 · 2019: 1574 · 2018: 1062 · 2017: 593 · 2016: 281 · 2015: 51
- FWCI
- 271.65
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (publishedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
- Keywords
- FaceNet, face recognition, face verification, face clustering, embedding space, triplet loss, deep convolutional neural networks, face similarity, Labeled Faces in the Wild
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.