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 101–200 of 1,094
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
Ye, M., Zhang, X., Yuen, P. C., & Chang, S.-F. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00637 · Cited by 601
“In particular, several sampling strategies are widely investigated to improve the performance, such as hard mining [16], semihard mining [35], smart mining [13] and so on.”
BackgroundFace Recognition Systems: A Survey
Kortli, Y., Jridi, M., Al Falou, A., & Atri, M. (2020) · Sensors · doi:10.3390/s20020342 · Cited by 623
“Correlation filters (CFs) [18,37,38], convolutional neural network (CNN) [39], and also k-nearest neighbor (K-NN) [40] are known to effectively address this task.”
BackgroundDeep Domain Generalization via Conditional Invariant Adversarial Networks
Li, Y., Tian, X., Gong, M., Liu, Y., Liu, T., Zhang, K., & Tao, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_38 · Cited by 576
End-to-End Comparative Attention Networks for Person Re-Identification
Liu, H., Feng, J., Qi, M., Jiang, J., & Yan, S. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2700762 · Cited by 482
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
Huang, Y., Wang, Y., Tai, Y., Liu, X., Shen, P., Li, S., Li, J., & Huang, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00594 · Cited by 580
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., & Gool, L. V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00721 · Cited by 604
Deep Face Recognition: A Survey
Masi, I., Wu, Y., Hassner, T., & Natarajan, P. (2018) · 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2018.00067 · Cited by 568
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
Sun, B., Li, B., Cai, S., Yuan, Y., & Zhang, C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00727 · Cited by 555
Time-Contrastive Networks: Self-Supervised Learning from Video
Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S., Levine, S., & Brain, G. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8462891 · Cited by 546
“For the TCN models, we use the triplet loss from [38] without modification and with a gap value of 0.”
Recurrent Convolutional Network for Video-Based Person Re-identification
McLaughlin, N., Martinez del Rincon, J., & Miller, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.148 · Cited by 564
Measuring Catastrophic Forgetting in Neural Networks
Kemker, R., McClure, M., Abitino, A., Hayes, T., & Kanan, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11651 · Cited by 672
Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Uiuc, U., & Huang, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00621 · Cited by 545
“The triplet loss with hard mining is first proposed in [20] as an improved version of the original semi-hard triplet loss [32].”
BackgroundLarge Separable Kernel Attention: Rethinking the Large Kernel Attention design in CNN
Lau, K. W., Po, L.-M., & Rehman, Y. A. U. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121352 · Cited by 569
Deep Isolation Forest for Anomaly Detection
Xu, H., Pang, G., Wang, Y., & Wang, Y. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3270293 · Cited by 556
Past, Present, and Future of Face Recognition: A Review
Adjabi, I., Ouahabi, A., Benzaoui, A., & Taleb-Ahmed, A. (2020) · Electronics · doi:10.3390/electronics9081188 · Cited by 560
Deep Metric Learning with Angular Loss
Wang, J., Zhou, F., Wen, S., Liu, X., & Lin, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.283 · Cited by 542
Features for Multi-target Multi-camera Tracking and Re-identification
Ristani, E., & Tomasi, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00632 · Cited by 556
Face aging with conditional generative adversarial networks
Antipov, G., Baccouche, M., & Dugelay, J.-L. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296650 · Cited by 515
“Despite the age estimation CNN has never seen synthetic images during the training, the resulting mean age estimation accuracy on synthetic images is just 17% lower than on natural ones.”
MethodInfluentialCNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
Radenović, F., Tolias, G., & Chum, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_1 · Cited by 551
Neimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00355 · Cited by 551
“, image classification [32, 19, 34], object detection [17, 16, 28], semantic segmentation [25], object instance segmentation [18], face recognition [33, 30] and video action recognition [9, 38, 3, 39, 23, 14, 13, 12].”
BackgroundKarkkainen, K., & Joo, J. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00159 · Cited by 527
“…image datasets [21, 31, 13, 70, 37, 23, 43, 69, 14, 26, 48, 8, 40] have been proposed and fostered research and development for automated face detection [35, 20], alignment [67, 46], recognition [57, 51], generation [68, 5, 25, 58], modification [3, 32, 18], and attribute classification [31, 37].”
BackgroundMasood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
Edge Computing Security: State of the Art and Challenges
Xiao, Y., Jia, Y., Liu, C., Cheng, X., Yu, J., & Lv, W. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918437 · Cited by 534
“, fingerprints [158], face authentication [159], authentication code via SMS messages [160], graphic texts [161], or even ambient sound [162].”
BackgroundLearning Two-Branch Neural Networks for Image-Text Matching Tasks
Wang, L., Li, Y., Huang, J., & Lazebnik, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2797921 · Cited by 535
RankIQA: Learning from Rankings for No-Reference Image Quality Assessment
Liu, X., Van De Weijer, J., & Bagdanov, A. D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.118 · Cited by 514
“In [24] they propose semi-hard pair selection, arguing that selecting hardest pairs can lead to bad local minima.”
BackgroundLow-Shot Learning with Imprinted Weights
Qi, H., Brown, M., & Lowe, D. G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00610 · Cited by 539
“such as [12, 16, 18, 20] can immediately remember new examples and use them for recognition without retraining.”
BackgroundMethodInfluentialEnd-to-End Learning of Deep Visual Representations for Image Retrieval
Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1016-8 · Cited by 537
“Recently triplet networks (i.e. three-stream siamese networks) have been considered for metric learning (Hoffer and Ailon, 2015; Wang et al, 2014) and face identification (Schroff et al, 2015).”
BackgroundLarge Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Cui, Y., Song, Y., Sun, C., Howard, A., & Belongie, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00432 · Cited by 503
Deep visual tracking: Review and experimental comparison
Li, P., Wang, D., Wang, L., & Lu, H. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.11.007 · Cited by 517
Deep Graph Contrastive Representation Learning
Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., & Wang, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04131 · Cited by 389
Deep Cross-Modal Projection Learning for Image-Text Matching
Zhang, Y., & Lu, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_42 · Cited by 495
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
Kong, S., Shen, X., Lin, Z., Mech, R., & Fowlkes, C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_40 · Cited by 468
Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification
Si, J., Zhang, H., Li, C.-G., Kuen, J., Kong, X., Kot, A. C., & Wang, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00562 · Cited by 466
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497
“To the vulnerability of face recognition to Deepfake videos, we evaluate two state of the art systems: based on VGG [9] and Facenet6 [10] neural networks on both untampered videos and videos with faces swapped.”
BackgroundMethodInfluentialRobust Classification with Convolutional Prototype Learning
Yang, H.-M., Zhang, X.-Y., Yin, F., & Liu, C.-L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00366 · Cited by 469
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Srinivas, A., Laskin, M., & Abbeel, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.04136 · Cited by 213
Fine-Grained Image Analysis With Deep Learning: A Survey
Wei, X.-S., Song, Y.-Z., Aodha, O. M., Wu, J., Peng, Y., Tang, J., Yang, J., & Belongie, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3126648 · Cited by 434
“, by capturing the discriminative parts of objects (faces, people, and vehicles) [8], [35], [36], discovering coarse-to-fine”
BackgroundFacial Expression Recognition Based on Deep Evolutional Spatial-Temporal Networks
Zhang, K., Huang, Y., Du, Y., & Wang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2689999 · Cited by 487
Gazelle: A Low Latency Framework for Secure Neural Network Inference
Juvekar, C., Vaikuntanathan, V., & Chandrakasan, A. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05507 · Cited by 164
A survey on deep learning based face recognition
Guo, G., & Zhang, N. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2019.102805 · Cited by 485
SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection
Zhang, C., Wang, L., Cheng, S., & Li, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3160007 · Cited by 483
Multi-Scale Convolutional Neural Networks for Time Series Classification
Cui, Z., Chen, W., & Chen, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.06995 · Cited by 455
“In recent years, convolutional neural networks (CNNs) have led to impressive results in object recognition [14], face verification [28], and audio classification [15].”
BackgroundGanju, K., Wang, Q., Yang, W., Gunter, C. A., & Borisov, N. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243834 · Cited by 475
“For the CelebA dataset, we make use of a pre-trained network, called FaceNet [37], to generate image representations or embeddings of size 512.”
MethodInfluentialKhosravi, P., Kazemi, E., Zhan, Q., Malmsten, J. E., Toschi, M., Zisimopoulos, P., Sigaras, A., Lavery, S., Cooper, L. A. D., Hickman, C., et al. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0096-y · Cited by 469
Two-Branch Recurrent Network for Isolating Deepfakes in Videos
Masi, I., Killekar, A., Mascarenhas, R. M., Gurudatt, S. P., & AbdAlmageed, W. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58571-6_39 · Cited by 471
Labeled Faces in the Wild: A Survey
Learned-Miller, E., Huang, G. B., RoyChowdhury, A., Li, H., & Hua, G. (2016) · Advances in Face Detection and Facial Image Analysis · doi:10.1007/978-3-319-25958-1_8 · Cited by 457
“This model from Google, called the FaceNet [82], uses 128-dimensional representations from very deep networks, trained on a 260-million image data set using a triplet loss at the final layer -the loss separates a positive pair from a negative pair by a margin.”
BackgroundMethodInfluentialDeep Metric Learning with Hierarchical Triplet Loss
Ge, W., Huang, W., Dong, D., & Scott, M. R. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_17 · Cited by 445
“…key-point descriptor learning [12,24], face verification [22,20], person re-identification [30,23], object tracking [29] and etc. Recently, there is a number of widely-used loss functions developed for deep metric learning, such as contrastive loss [27,6], triplet loss [22] and quadruplet loss [5].”
BackgroundResultInfluentialDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
“Test results show that the popular face recognition systems based on VGG [38] and Facenet [31, 39] are unable to detect deepfakes effectively.”
ResultDeep learning for deepfakes creation and detection: A survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464
“Test results show that the popular face recognition systems based on VGG [60] and Facenet [40], [61] are unable to”
A Guide to Convolutional Neural Networks for Computer Vision
Khan, S. H., Rahmani, H., Shah, S. A. A., & Bennamoun, M. (2018) · Synthesis lectures on computer vision · doi:10.2200/s00822ed1v01y201712cov015 · Cited by 443
3D Morphable Face Models—Past, Present, and Future
Egger, B., Smith, W. A. P., Tewari, A., Wuhrer, S., Zollhoefer, M., Beeler, T., Bernard, F., Bolkart, T., Kortylewski, A., Romdhani, S., et al. (2020) · ACM Transactions on Graphics · doi:10.1145/3395208 · Cited by 448
“Therefore, purely data-driven approaches have remained the dominant approach to face recognition, in particular since the advancement of deep learning technology [Parkhi et al. 2015; Schroff et al. 2015; Taigman et al. 2014].”
Robust Face Recognition via Multimodal Deep Face Representation
Ding, C., & Tao, D. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2477042 · Cited by 449
“It is expected that this multi-stage training strategy can boost performance while converge faster than using the triplet loss alone [38].”
BackgroundMethodWhere to Buy It: Matching Street Clothing Photos in Online Shops
Kiapour, M. H., Han, X., Lazebnik, S., Berg, A. C., & Berg, T. L. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.382 · Cited by 442
“Some examples include methods for fine-grained object retrieval [34, 20], face verification [29, 32], or image patch-matching [40, 13, 41].”
MethodMulti-Factor Authentication: A Survey
Ometov, A., Bezzateev, S., Mäkitalo, N., Andreev, S., Mikkonen, T., & Koucheryavy, Y. (2018) · Cryptography · doi:10.3390/cryptography2010001 · Cited by 434
“Here, FAR i and FRR i are taken at the CER/EER point, e.g., z i is selected at the point where FAR i = FRR i .”
MethodInfluentialUnsupervised Person Re-Identification by Soft Multilabel Learning
Yu, H.-X., Zheng, W.-S., Wu, A., Guo, X., Gong, S., & Lai, J.-H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00225 · Cited by 421
“It has been shown extensively that mining hard negatives is more important in learning a discriminative embedding than naively learning from all visual samples [13, 37, 26, 35, 34].”
BackgroundTrunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition
Ding, C., & Tao, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2700390 · Cited by 441
“Recent advances in face recognition have tended to ignore the peculiarities of videos when extending techniques from SIFR to VFR [5], [6], [7], [8].”
BackgroundMethodInfluentialMulti-Attention Multi-Class Constraint for Fine-grained Image Recognition
Sun, M., Yuan, Y., Zhou, F., & Ding, E. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_49 · Cited by 426
Proxy Anchor Loss for Deep Metric Learning
Kim, S., Kim, D., Cho, M., & Kwak, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00330 · Cited by 407
Discrimination-aware Channel Pruning for Deep Neural NetworksPreprint
Zhuang, Z., Tan, M., Zhuang, B., Liu, J., Guo, Y. F., Wu, Q., Huang, J., & Zhu, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11809 · Cited by 697
“, FaceNet [34], DeepFace [41], and VGG [29], our pruned model achieves comparable performance but has only 45.”
BackgroundMethodInfluentialLearning Attentive Pairwise Interaction for Fine-Grained Classification
Zhuang, P., Wang, Y., & Qiao, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7016 · Cited by 415
A Metric Learning Reality Check
Musgrave, K., Belongie, S., & Lim, S.-N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58595-2_41 · Cited by 414
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review
Bernal, J., Kushibar, K., Asfaw, D. S., Valverde, S., Oliver, A., Martí, R., & Lladó, X. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2018.08.008 · Cited by 368
RetinaFace: Single-stage Dense Face Localisation in the Wild
Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I., & Zafeiriou, S. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.00641 · Cited by 391
“Automatic face localisation is the prerequisite step of facial image analysis for many applications such as facial attribute ( e.g . expression [64] and age [38]) and facial identity recognition [45, 31, 55, 11].”
BackgroundEfficient Decision-Based Black-Box Adversarial Attacks on Face Recognition
Dong, Y., Su, H., Wu, B., Li, Z., Liu, W., Zhang, T., & Zhu, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00790 · Cited by 411
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
Han, X.-F., Laga, H., & Bennamoun, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2954885 · Cited by 431
“In general, existing techniques use generic networks such as AlexNet, or networks specifically trained on facial images such as VGG-Face [125] or FaceNet [126].”
BackgroundMethodSurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis
Ji, M., Gall, J., Zheng, H., Liu, Y., & Fang, L. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.253 · Cited by 361
Range Loss for Deep Face Recognition with Long-Tailed Training Data
Zhang, X., Fang, Z., Wen, Y., Li, Z., & Qiao, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.578 · Cited by 405
Track to Detect and Segment: An Online Multi-Object Tracker
Wu, J., Cao, J., Song, L., Wang, Y., Yang, M., & Yuan, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01217 · Cited by 406
“This way not only learns an effective embedding as common re-ID loss [45, 25, 32, 51], but also is well compatible with the detection loss and does not hurt detection performance as shown in Tab.”
BackgroundSynthetic Data for Deep Learning
Nikolenko, S. I. (2021) · Springer Optimization and Its Applications · doi:10.1007/978-3-030-75178-4 · Cited by 423
“While face recognition for full-face frontal high-quality photos has been mostly solved in 2D, achieving human and superhuman performance both for classification [575] and retrieval via embeddings [529], pose-invariant face recognition in the wild [149,261,620], i.”
BackgroundMancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification
Wang, C., Zhang, Q., Huang, C., Liu, W., & Wang, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_23 · Cited by 410
“It is widely used for learning image embeddings, such as [3, 4, 6, 28, 36, 41].”
BackgroundMethodInfluentialMOLI: multi-omics late integration with deep neural networks for drug response prediction
Sharifi-Noghabi, H., Zolotareva, O., Collins, C. C., & Ester, M. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz318 · Cited by 421
“To the best of our knowledge, MOLI is the first end-to-end late integration method with deep neural networks that optimizes this representation via a combined cost function consisting of a triplet loss function (Schroff et al., 2015) and a binary cross-entropy loss function.”
BackgroundMethodInfluentialFacial Landmark Detection: A Literature Survey
Wu, Y., & Ji, Q. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-018-1097-z · Cited by 404
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
Qian, Q., Shang, L., Sun, B., Hu, J., Tacoma, T., Li, H., & Jin, R. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00655 · Cited by 402
“For SemiHard [21], we report the result recorded in [23].”
BackgroundInfluentialDeep Cosine Metric Learning for Person Re-identification
Wojke, N., & Bewley, A. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00087 · Cited by 329
An All-In-One Convolutional Neural Network for Face Analysis
Ranjan, R., Sankaranarayanan, S., Castillo, C. D., & Chellappa, R. (2017) · 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) · doi:10.1109/fg.2017.137 · Cited by 409
“Recent methods such as DeepFace [43], Facenet [42], VGG-Face [34] have significantly improved the verification accuracy on the LFW [17] dataset by training deep CNN models on millions of annotated data.”
MethodBatch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Ioffe, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.03275 · Cited by 367
“However, sampling with dependencies may be necessary for tasks such as for metric learning [4, 11].”
BackgroundLearning from Multiple Teacher Networks
You, S., Xu, C., Xu, C., & Tao, D. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098135 · Cited by 395
Neural Aggregation Network for Video Face Recognition
Yang, J., Ren, P., Zhang, D., Chen, D., Wen, F., Li, H., & Hua, G. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.554 · Cited by 409
Contrastive Learning with Hard Negative SamplesPreprint
Robinson, J., Chuang, C.-Y., Sra, S., & Jegelka, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04592 · Cited by 1,237
Composing Text and Image for Image Retrieval - an Empirical Odyssey
Vo, N., Jiang, L., Sun, C., Murphy, K., Li, L.-J., Fei-Fei, L., & Hays, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00660 · Cited by 399
Rethinking Semantic Segmentation: A Prototype View
Zhou, T., Wang, W., Konukoglu, E., & Van Goo, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00261 · Cited by 376
“In addition, it greatly outperforms many famous segmentation models, such as HANet [4], HRNetV2 [13], SETR [18].”
InfluentialLearning With Average Precision: Training Image Retrieval With a Listwise Loss
Revaud, J., Almazan, J., Rezende, R., & Souza, C. D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00521 · Cited by 408
“, triplet-based [17, 50], ntuple-based [52]) loss functions, which we call local loss functions because they act on a fixed and limited number of examples before computing the gradient.”
BackgroundPose Transferrable Person Re-identification
Liu, J., Ni, B., Yan, Y., Zhou, P., Cheng, S., & Hu, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00431 · Cited by 398
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., & Zisserman, A. (2021) · arXiv · doi:10.48550/arxiv.2104.14548 · Cited by 405
RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection
Karlinsky, L., Shtok, J., Harary, S., Schwartz, E., Aides, A., Feris, R., Giryes, R., & Bronstein, A. M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00534 · Cited by 386
“This has been demonstrated for domain-specific tasks, such as face recognition [28] and for the classification of general categories”
BackgroundWith a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., & Zisserman, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00945 · Cited by 404
“One broad category of self-supervised learning techniques are those that use contrastive losses, which have been used in a wide range of computer vision applications[8, 26, 47].”
BackgroundJoint Learning of Single-Image and Cross-Image Representations for Person Re-identification
Wang, F., Zuo, W., Lin, L., Zhang, D., & Zhang, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.144 · Cited by 389
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Hu, S., Feng, M., Nguyen, R. M. H., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00758 · Cited by 394
“We adopted weight sharing in our CVM-Net-II network because weight sharing has been proven to improve metric learning in many of the Siamese network architectures [12, 34, 15, 51, 31].”
MethodEnd-to-End Reconstruction-Classification Learning for Face Forgery Detection
Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00408 · Cited by 428
Negative Margin Matters: Understanding Margin in Few-Shot Classification
Liu, B., Cao, Y., Lin, Y., Li, Q., Zhang, Z., Long, M., & Hu, H. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58548-8_26 · Cited by 350
Self-Supervised Learning of Graph Neural Networks: A Unified Review
Xie, Y., Xu, Z., Zhang, J., Wang, Z., & Ji, S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3170559 · Cited by 389
Channel Augmented Joint Learning for Visible-Infrared Recognition
Ye, M., Ruan, W., Du, B., & Shou, M. Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01331 · Cited by 375
“A widely-used technique to measure the pair distance difference is ℓ 1 norm [29, 31, 34], as done Eq.”
MethodA comprehensive survey of loss functions and metrics in deep learning
Terven, J., Cordova-Esparza, D.-M., Romero-González, J.-A., Ramírez-Pedraza, A., & Chávez-Urbiola, E. A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11198-7 · Cited by 343
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
Wu, B., Wan, A., Yue, X., Jin, P., Zhao, S., Golmant, N., Gholaminejad, A., Gonzalez, J., & Keutzer, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00951 · Cited by 381
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
Yew, Z. J., & Lee, G. H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_37 · Cited by 392
“The network is trained by minimizing a Triplet loss [29] where the positive and “hardest” negative samples are chosen from the similarity measures between all pairs of descriptors [14] from two input point clouds.”
BackgroundA deep learning method for online capacity estimation of lithium-ion batteries
Shen, S., Sadoughi, M., Chen, X., Hong, M., & Hu, C. (2019) · Journal of Energy Storage · doi:10.1016/j.est.2019.100817 · Cited by 392
Unifying Deep Local and Global Features for Image Search
Cao, B., Araujo, A., & Sim, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58565-5_43 · Cited by 366
“Today, most high-performing global features are based on deep convolutional neural networks [5,4,59,1,17,47,48], which are trained with ranking-based [9,51,19] or classification losses [61,11].”
BackgroundDeep Speaker: an End-to-End Neural Speaker Embedding System
Li, C., Ma, X., Jiang, B., Li, X., Zhang, X., Liu, X., Cao, Y., Kannan, A., & Zhu, Z. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.02304 · Cited by 374
Semantic Instance Segmentation with a Discriminative Loss Function
Brabandere, B. D., Neven, D., & Gool, L. V. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.02551 · Cited by 392
“Inspired by the success of siamese networks [8, 10] and the triplet loss [39, 33] in image classification, we introduce a discriminative loss function to replace the pixel-wise softmax loss that is commonly used in semantic segmentation.”
MethodIn Defence of Metric Learning for Speaker Recognition
Chung, J. S., Huh, J., Mun, S., Lee, M., Heo, H.-S., Choe, S., Ham, C., Jung, S., Lee, B.-J., & Han, I. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-1064 · Cited by 383
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.