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 201–300 of 1,094
Triplet-Center Loss for Multi-view 3D Object Retrieval
He, X., Zhou, Y., Zhou, Z., Bai, S., & Bai, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00208 · Cited by 390
A review of deep learning techniques for speech processing
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101869 · Cited by 389
Direct Fit to Nature: An Evolutionary Perspective on Biological and Artificial Neural Networks
Hasson, U., Nastase, S. A., & Goldstein, A. (2020) · Neuron · doi:10.1016/j.neuron.2019.12.002 · Cited by 387
Speaker recognition based on deep learning: An overview
Bai, Z., & Zhang, X.-L. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.03.004 · Cited by 386
“Besides the “hard negative” sampling, the “semi-hard” negative sample selection [158, 141] and softmax pre-training [69] are all used to stabilize the training process of the triple loss.”
MethodDeep Attributes Driven Multi-camera Person Re-identification
Su, C., Zhang, S., Xing, J., Gao, W., & Tian, Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_30 · Cited by 227
“When we fine-tune dCNN with attributes triplet loss, we follow the standard triplet loss algorithm [47] to select samples.”
MethodWang, Z., Tang, L., Liu, X., Yao, Z., Yi, S., Shao, J., Yan, J., Wang, S., Li, H., & Wang, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.49 · Cited by 366
“Key point-based face alignment is conducted in most face recognition frameworks [15, 18].”
BackgroundTowards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa
Shen, G., Zhang, J., Marshall, A., & Cavallaro, J. R. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3152404 · Cited by 374
“Triplet loss is a well-known embedding loss used in deep metric learning and has been successfully adopted in face recognition [43], [44].”
BackgroundLearning SO(3) Equivariant Representations with Spherical CNNs
Esteves, C., Allen-Blanchette, C., Makadia, A., & Daniilidis, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01261-8_4 · Cited by 373
Very deep convolutional neural networks for raw waveforms
Dai, W., Dai, C., Qu, S., Li, J., & Das, S. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952190 · Cited by 357
Imbalanced Deep Learning by Minority Class Incremental Rectification
Dong, Q., Gong, S., & Zhu, X. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2832629 · Cited by 369
A Novel Bi-Hemispheric Discrepancy Model for EEG Emotion Recognition
Li, Y., Wang, L., Zheng, W., Zong, Y., Qi, L., Cui, Z., Zhang, T., & Song, T. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.2999337 · Cited by 369
A Review of Face Recognition Technology
Li, L., Mu, X., Li, S., & Peng, H. (2020) · IEEE Access · doi:10.1109/access.2020.3011028 · Cited by 360
Self-Supervised Learning in Remote Sensing: A review
Wang, Y., Albrecht, C. M., Braham, N. A. A., Mou, L., & Zhu, X. X. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3198244 · Cited by 364
Robust Multi-View Clustering With Incomplete Information
Yang, M., Li, Y., Hu, P., Bai, J., Lv, J., & Peng, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3155499 · Cited by 332
“With the augmented data, a variety of losses [21]–[23], [25], [26] have been proposed to learn the representations by maximizing the similarities of positives while minimizing those of negatives.”
BackgroundLi, J., Xie, H., Li, J., Wang, Z., & Zhang, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00639 · Cited by 357
“Center loss [42] and triplet loss [37] are the two most relevant metric learning methods to our work.”
BackgroundInfluentialShi, Y., & Jain, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00700 · Cited by 335
“In particular, we implement the following state-of-the-art loss functions: Softmax+Center Loss [35], Triplet Loss [27], A-Softmax [20] and AM-Softmax [33](9).”
BackgroundMethodDeep Imbalanced Learning for Face Recognition and Attribute Prediction
Huang, C., Li, Y., Loy, C. C., & Tang, X. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2914680 · Cited by 354
Self-Alignment Pretraining for Biomedical Entity Representations
Liu, F., Shareghi, E., Meng, Z., Basaldella, M., & Collier, N. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.334 · Cited by 335
Racial faces in the wild: Reducing racial bias by information maximization adaptation network
Wang, M., Deng, W., Hu, J., Tao, X., & Huang, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00078 · Cited by 353
“The emergence of deep convolutional neural networks (CNN) [38, 55, 59, 31, 32] greatly advances the frontier of face recognition (FR) [63, 58, 54].”
BackgroundSmart Mining for Deep Metric Learning
Harwood, B., Kumar B.G., V., Carneiro, G., Reid, I., & Drummond, T. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.307 · Cited by 344
Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing
Zheng, Y., Zhan, J., He, S., Dong, J., & Du, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00560 · Cited by 339
Keep it real: rethinking the primacy of experimental control in cognitive neuroscience
Nastase, S. A., Goldstein, A., & Hasson, U. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117254 · Cited by 344
Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
Masi, I., Trần, A. T., Hassner, T., Leksut, J. T., & Medioni, G. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_35 · Cited by 339
Quality Aware Network for Set to Set Recognition
Liu, Y., Yan, J., & Ouyang, W. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.499 · Cited by 339
AI Benchmark: Running Deep Neural Networks on Android Smartphones
Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., & Van Gool, L. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11021-5_19 · Cited by 347
LightFace: A Hybrid Deep Face Recognition Framework
Serengil, S. I., & Ozpinar, A. (2020) · 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu50717.2020.9259802 · Cited by 347
“Proposed and published software library package wraps the most popular face recognition models: VGG-Face [17], FaceNet [18], OpenFace [19], DeepFace [13], DeepID [20] [21] and Dlib [22].”
MethodFeature Transfer Learning for Face Recognition With Under-Represented Data
Yin, X., Yu, X., Sohn, K., Liu, X., & Chandraker, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00585 · Cited by 346
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · arXiv · doi:10.48550/arxiv.1908.10084 · Cited by 343
“In order to fine-tune BERT / RoBERTa, we create siamese and triplet networks (Schroff et al., 2015) to update the weights such that the produced sentence embeddings are semantically meaningful and can be compared with cosine-similarity.”
MethodSchmidt, J., Shi, J., Borlido, P., Chen, L., Botti, S., & Marques, M. A. L. (2017) · Chemistry of Materials · doi:10.1021/acs.chemmater.7b00156 · Cited by 341
VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild
Lou, Y., Bai, Y., Liu, J., Wang, S., & Duan, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00335 · Cited by 326
“Triplet [17] 15.”
Semantic Drift Compensation for Class-Incremental Learning
Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., & van de Weijer, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00701 · Cited by 340
Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images
Khosravi, P., Kazemi, E., Imielinski, M., Elemento, O., & Hajirasouliha, I. (2018) · EBioMedicine · doi:10.1016/j.ebiom.2017.12.026 · Cited by 334
“This is the reason of using Inception networks in big data analysis where huge amount of data needed to be processed at reasonable time and computational cost (Movshovitz-Attias et al., 2015; Schroff et al., 2015).”
MethodHu, G., Yang, Y., Yi, D., Kittler, J., Christmas, W., Li, S. Z., & Hospedales, T. (2015) · 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2015.58 · Cited by 331
Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns
Levi, G., & Hassner, T. (2015) · Proceedings of the 2015 ACM on International Conference on Multimodal Interaction · doi:10.1145/2818346.2830587 · Cited by 336
“sion and face recognition systems include the significant difference in the data available for developing, training and testing automatic systems: Much of the recent achievements in machine face recognition have been due to deep Convolutional Neural Networks (CNN) which require massive amounts of labeled training data…”
BackgroundR2D2: Repeatable and Reliable Detector and Descriptor
Revaud, J., Weinzaepfel, P., de Souza, C. R., Pion, N., Csurka, G., Cabon, Y., & Humenberger, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06195 · Cited by 334
Zhou, Z., Huang, Y., Wang, W., Wang, L., & Tan, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.717 · Cited by 323
Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision
Sanyal, S., Bolkart, T., Feng, H., & Black, M. J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00795 · Cited by 332
“triplet loss) [37] and face recognition [26], but, to our knowledge, our approach has not previously been used to learn a mapping from 2D to 3D geometry.”
MethodMachine learning for multi-omics data integration in cancer
Cai, Z., Poulos, R. C., Liu, J., & Zhong, Q. (2022) · iScience · doi:10.1016/j.isci.2022.103798 · Cited by 327
“, 1986) as a feature extractor for each omics layer, and concatenates the last hidden layers with a triplet loss (Schroff et al., 2015) at the end to train the model.”
BackgroundMethodA Comprehensive Survey on Pose-Invariant Face Recognition
Ding, C., & Tao, D. (2016) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2845089 · Cited by 329
“High-quality face representation is critical for the traditional NFFR problem, and deep learning-based methods achieve great success in representation learning [Taigman et al. 2015; Sun et al. 2015; Schroff et al. 2015; Ding and Tao 2015].”
MethodPart-Regularized Near-Duplicate Vehicle Re-Identification
He, B., Li, J., Zhao, Y., & Tian, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00412 · Cited by 310
“FaceNet [20] improved the LMNN loss into a modified triplet loss which directly optimize the final distance metric and can be applied in re-identification and face recognition tasks.”
MethodZhang, K., Liu, X., Xu, J., Yuan, J., Cai, W., Chen, T., Wang, K., Gao, Y., Nie, S., Xu, X., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-021-00745-6 · Cited by 324
Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System
Cai, W., Chen, J., & Li, M. (2018) · The Speaker and Language Recognition Workshop (Odyssey 2018) · doi:10.21437/odyssey.2018-11 · Cited by 315
Data Uncertainty Learning in Face Recognition
Chang, J., Lan, Z., Cheng, C., & Wei, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00575 · Cited by 320
Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
Zheng, T., Deng, W., & Hu, J. (2017) · arXiv · doi:10.48550/arxiv.1708.08197
Peak-Piloted Deep Network for Facial Expression Recognition
Zhao, X., Liang, X., Liu, L., Li, T., Han, Y., Vasconcelos, N., & Yan, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_27 · Cited by 304
“Due to its excellent performance on several face-related recognition tasks [29,30], the popular GoogLeNet [24] is adopted as the basic network architecture.”
BackgroundMethodKhrulkov, V., Mirvakhabova, L., Ustinova, E., Oseledets, I., & Lempitsky, V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00645 · Cited by 306
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition
He, R., Wu, X., Sun, Z., & Tan, T. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2842770 · Cited by 317
Learning Deep Embeddings with Histogram Loss
Ustinova, E., & Lempitsky, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.00822 · Cited by 222
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
Xu, H., He, K., Plummer, B. A., Sigal, L., Sclaroff, S., & Saenko, K. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019062 · Cited by 307
Densely Semantically Aligned Person Re-Identification
Zhang, Z., Lan, C., Zeng, W., & Chen, Z. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00076 · Cited by 302
Quantifying behavior to understand the brain
Pereira, T. D., Shaevitz, J. W., & Murthy, M. (2020) · Nature Neuroscience · doi:10.1038/s41593-020-00734-z · Cited by 309
Hard-Aware Deeply Cascaded Embedding
Yuan, Y., Yang, K., & Zhang, C. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.94 · Cited by 307
“Deep metric embedding has attracted increasing attention for various tasks , such as visual product search [6, 18, 23, 27, 35], face recognition [21, 32, 41, 4], local image descriptor learning [9, 2, 12, 24], person/vehicle reidentification [22, 7, 43, 17], zero-shot image classification [19, 45, 5], fine-grained ima…”
BackgroundLearning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
Park, H., Lee, S., Lee, J., & Ham, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01183 · Cited by 295
Unsupervised Training for 3D Morphable Model Regression
Genova, K., Cole, F., Maschinot, A., Sarna, A., Vlasic, D., & Freeman, W. T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00874 · Cited by 311
GANFIT: generative adversarial network fitting for high fidelity 3D face reconstruction
Gecer, B., Ploumpis, S., Kotsia, I., & Zafeiriou, S. (2019) · Spiral (Imperial College London) · Cited by 311
Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization
Wang, T., Zheng, Z., Yan, C., Zhang, J., Sun, Y., Zheng, B., & Yang, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3061265 · Cited by 306
“Specifically, the network is to learn one feature space that brings matched image pairs closer and pushes nonmatched pairs far apart [8], [9], [10].”
BackgroundSystematic evaluation of convolution neural network advances on the Imagenet
Mishkin, D., Sergievskiy, N., & Matas, J. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.05.007 · Cited by 308
“al [52] but on an extra-large dataset: decreasing the dataset size from 260M”
BackgroundMulti-Task Convolutional Neural Network for Pose-Invariant Face Recognition
Yin, X., & Liu, X. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2765830 · Cited by 255
Neural Face Editing with Intrinsic Image Disentangling
Shu, Z., Yumer, E., Hadap, S., Sunkavalli, K., Shechtman, E., & Samaras, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.578 · Cited by 307
“Face representation learning is generally performed with a standard convolutional neural network trained for a recognition or labeling task [29, 24, 27].”
BackgroundImage super-resolution using progressive generative adversarial networks for medical image analysis
Mahapatra, D., Bozorgtabar, B., & Garnavi, R. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2018.10.005 · Cited by 308
Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
Akhtar, N., Mian, A., Kardan, N., & Shah, M. (2021) · IEEE Access · doi:10.1109/access.2021.3127960 · Cited by 302
“A related concept of ‘adversarial light projection’ is studied in [251] that projects a rather conspicuous pattern on faces to evade FaceNet model [252] in white-box settings.”
BackgroundGANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
Gecer, B., Ploumpis, S., Kotsia, I., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00125 · Cited by 303
Google Landmarks Dataset v2 – A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
Weyand, T., Araujo, A., Cao, B., & Sim, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00265 · Cited by 303
Yu, K., Lin, T. R., Ma, H., Li, X., & Li, X. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107043 · Cited by 302
ElasticFace: Elastic Margin Loss for Deep Face Recognition
Boutros, F., Damer, N., Kirchbuchner, F., & Kuijper, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00164 · Cited by 294
“To achieve that, different solutions opted to train deep neural networks by either directly learning the embedding (e.g. Triplet loss [24]) or by learning an identity classification problem (e.g. Softmax loss [2]).”
BackgroundInfluentialAdversarially Occluded Samples for Person Re-identification
Huang, H., Li, D., Zhang, Z., Chen, X., & Huang, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00535 · Cited by 290
“[8] introduced triplet loss [30] into person ReID.”
MethodFrom Facial Expression Recognition to Interpersonal Relation Prediction
Zhang, Z., Luo, P., Loy, C. C., & Tang, X. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-017-1055-1 · Cited by 302
Jagannath, A., Jagannath, J., & Kumar, P. S. P. V. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109455 · Cited by 300
On Mutual Information Maximization for Representation Learning
Tschannen, M., Djolonga, J., Rubenstein, P. K., Gelly, S., & Lučić, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.13625 · Cited by 253
“Secondly, it elucidates the importance of appropriately choosing the negative samples, which is indeed a critical component in deep metric learning based on triplet losses (Norouzi et al., 2012; Schroff et al., 2015).”
BackgroundMulti-Scale Metric Learning for Few-Shot Learning
Jiang, W., Huang, K., Geng, J., & Deng, X. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2995754 · Cited by 298
Calibrated RGB-D Salient Object Detection
Ji, W., Li, J., Yu, S., Zhang, M., Piao, Y., Yao, S., Bi, Q., Ma, K., Zheng, Y., Lu, H., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00935 · Cited by 276
“The triplet loss L triplet then can be calculated as: where d ( · ) indicates the Euclidean distance; m denotes the margin parameter and is set as 1.0 following [60].”
MethodInfluentialLocalizing and Orienting Street Views Using Overhead Imagery
Vo, N. N., & Hays, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_30 · Cited by 283
“The fourth network that we call the triplet network or ranking network, shown in Figure 3(c), is popular for image feature learning and retrieval [35, 31, 24, 32, 26, 25], though its effectiveness has not been explored in cross-view image matching.”
BackgroundMethodUniversal Correspondence Network
Choy, C., Gwak, J., Savarese, S., & Chandraker, M. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.03558 · Cited by 240
“Recently, a triplet loss is used by [30] for fine-grained image ranking, while the triplet loss is also used for face recognition and clustering in [26].”
MethodSupervised Contrastive Learning for Pre-trained Language Model Fine-tuningPreprint
Gunel, B., Du, J., Conneau, A., & Stoyanov, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01403 · Cited by 644
“Using hard negatives has been previously shown to improve performance in the context of margin-based loss formulations such as triplet loss (Schroff et al., 2015).”
MethodSelf supervised contrastive learning for digital histopathology
Ciga, O., Xu, T., & Martel, A. L. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100198 · Cited by 294
Advhat: Real-world adversarial attack on arcface face id system
Komkov, S., & Petiushko, A. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412236 · Cited by 294
Deep Metric Learning via Facility Location
Song, H. O., Jegelka, S., Rathod, V., & Murphy, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.237 · Cited by 287
“FaceNet [25] suggested the following online hard negative mining strategy.”
BackgroundMethodInfluentialA Survey on the New Generation of Deep Learning in Image Processing
Jiao, L., & Zhao, J. (2019) · IEEE Access · doi:10.1109/access.2019.2956508 · Cited by 293
“From deep hidden identity feature (deepID [126]) to faceNet [127], CNN plays a very important role in feature extraction.”
BackgroundConvolutional Two-Stream Network Fusion for Video Action Recognition
Feichtenhofer, C., Pinz, A. J., & Zisserman, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.06573 · Cited by 291
“However, action recognition has not yet seen the substantial gains in performance that have been achieved in other areas by ConvNets, e.g. image classification [12, 23, 27], human face recognition [21], and human pose estimation [29].”
BackgroundCrowd Counting with Deep Negative Correlation Learning
Shi, Z., Zhang, L., Liu, Y., Cao, X., Ye, Y., Cheng, M.-M., & Zheng, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00564 · Cited by 283
“Recently, the number of success stories of computer vision has seen an all-time rise across a wide range of topics such as image recognition [8], object detection [9], face recognition [10], image segmentation [11] and visual tracking [12].”
BackgroundRelational Embedding for Few-Shot Classification
Kang, D., Kwon, H., Min, J., & Cho, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00870 · Cited by 266
Self-Supervised Learning on Graphs: Contrastive, Generative, or Predictive
Wu, L., Lin, H., Tan, C., Gao, Z., & Li, S. Z. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3131584 · Cited by 290
Han, T., Li, Y.-F., & Qian, M. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3088489 · Cited by 288
“2, the loss function defines a triplet of three samples, i.e., anchor x ai , positive x , and negative x nk , in which x ai and x p j are the same class, and x nk belongs to different class [49].”
BackgroundOn the class overlap problem in imbalanced data classification
Vuttipittayamongkol, P., Elyan, E., & Petrovski, A. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106631 · Cited by 290
“benchmark data type min imb max imb compared methods data level CNN(1968) [136] real slightly extremely kNN:EA undersampling [97] Tomek-link(1976) [137] real slightly extremely kNN:EA undersampling [97] NCL(2001) [85] real slightly extremely kNN:EA undersampling [97] SMOTE(2002) [10] real slightly very highly DNN: CoS…”
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Zhu, Z., Huang, G., Deng, J., Ye, Y., Huang, J., Chen, X., Zhu, J., Yang, T., Lu, J., Du, D., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01035 · Cited by 290
“25 [11] for face detection and alignment, ResNet-14, MobileFaceNet (Flip), EfficientNet-B0 and RegNet-800MF for face feature extraction.”
BackgroundInfluentialEmbedding Deep Metric for Person Re-identification: A Study Against Large Variations
Shi, H., Yang, Y., Zhu, X., Liao, S., Lei, Z., Zheng, W., & Li, S. Z. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_44 · Cited by 257
“– For training the CNN, the hard negative mining strategy has been used in [1,27,30].”
MethodInfluentialIdentity-Aware Textual-Visual Matching with Latent Co-attention
Li, S., Xiao, T., Li, H., Yang, W., & Wang, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.209 · Cited by 277
Chaves, D., Fidalgo, E., Alegre, E., Alaiz-Rodríguez, R., Jáñez-Martino, F., & Azzopardi, G. (2020) · Sensors · doi:10.3390/s20164491 · Cited by 286
“Thus, CSEM can be identified with image classification techniques [5], and its content can be explored using object detection methods [6–9] and object recognition techniques [10–13].”
BackgroundREGTR: End-to-end Point Cloud Correspondences with Transformers
Yew, Z. J., & Lee, G. H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00656 · Cited by 277
Deep Clustering: A Comprehensive Survey
Ren, Y., Pu, J., Yang, Z., Xu, J., Li, G., Pu, X., Yu, P. S., & He, L. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3403155 · Cited by 276
“Usually, the objective of triplet networks [116] is defined to make the features of the positive pair more similar and that of the negative pair more dissimilar.”
Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network
Song, L., Gong, D., Li, Z., Liu, C., & Liu, W. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00086 · Cited by 267
Cluster Contrast for Unsupervised Person Re-identification
Dai, Z., Wang, G., Yuan, W., Zhu, S., & Tan, P. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-26351-4_20 · Cited by 252
Deep Learning for Biometrics: A Survey
Sundararajan, K., & Woodard, D. L. (2019) · ACM Computing Surveys · doi:10.1145/3190618 · Cited by 275
“[128] have outperformed other methods due to reasons mentioned earlier.”
BackgroundMethodInfluentialUnconstrained face verification using deep CNN features
Chen, J.-C., Patel, V. M., & Chellappa, R. (2016) · 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2016.7477557 · Cited by 269
Resource Aware Person Re-identification Across Multiple Resolutions
Wang, Y., Wang, L., You, Y., Zou, X., Chen, V., Li, S., Huang, G., Hariharan, B., & Weinberger, K. Q. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00839 · Cited by 266
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
Chen, Y., Pont-Tuset, J., Montes, A., & Gool, L. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00130 · Cited by 273
HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
Nirkin, Y., Wolf, L., & Hassner, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00405 · Cited by 254
Batch DropBlock Network for Person Re-Identification and Beyond
Dai, Z., Chen, M., Gu, X., Zhu, S., & Tan, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00379 · Cited by 256
Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
Song, J., Yu, Q., Song, Y.-Z., Xiang, T., & Hospedales, T. M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.592 · Cited by 261
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
Maximov, M., Elezi, I., & Leal-Taixe, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00549 · Cited by 222
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.