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 301–400 of 1,094
Cross-Batch Memory for Embedding Learning
Wang, X., Zhang, H., Huang, W., & Scott, M. R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00642 · Cited by 254
“Triplet loss [29] requires the similarity of a positive pair to be higher than that of a negative pair (with the same anchor) by a given margin.”
BackgroundMethodInfluentialLiu, H., Tan, X., & Zhou, X. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3042080 · Cited by 241
“1) Triplet loss revisit: Triplet loss was first proposed in FaceNet [17], and then improved by mining the hard triplets [8].”
BackgroundTowards Pose Invariant Face Recognition in the Wild
Zhao, J., Cheng, Y., Xu, Y., Xiong, L., Li, J., Zhao, F., Jayashree, K., Pranata, S., Shen, S., Xing, J., et al. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00235 · Cited by 260
“FaceNet [23] utilizes the inception architecture.”
BackgroundDemographic Bias in Biometrics: A Survey on an Emerging Challenge
Drozdowski, P., Rathgeb, C., Dantcheva, A., Damer, N., & Busch, C. (2020) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2020.2992344 · Cited by 263
Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects
Yang, J., Wang, C., Jiang, B., Song, H., & Meng, Q. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2998818 · Cited by 258
“…conducted a comprehensive evaluation of the effectiveness of face recognition methods in detecting DeepFake [115] which is also a popular face swapping software, and they found that general face recognition algorithms, such as FaceNet [116], identifying face generated by GAN was extremely poor.”
BackgroundCakir, F., He, K., Xia, X., Kulis, B., & Sclaroff, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00196 · Cited by 248
“A partial list includes lifted embedding [34], semi-hard negative mining [30], distanceweighted sampling [39], group-based sampling [2], and hierarchical sampling [8].”
BackgroundGroup-Sensitive Triplet Embedding for Vehicle Reidentification
Bai, Y., Lou, Y., Gao, F., Wang, S., Wu, Y., & Duan, L.-Y. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2796240 · Cited by 259
LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM
Cattaneo, D., Vaghi, M., & Valada, A. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3150683 · Cited by 258
“We train our global descriptors using the triplet loss [59].”
MethodLarge Scale Visual Food Recognition
Min, W., Wang, Z., Liu, Y., Luo, M., Kang, L., Wei, X., Wei, X., & Jiang, S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3237871 · Cited by 253
Adversarial Representation Learning for Text-to-Image Matching
Sarafianos, N., Xu, X., & Kakadiaris, I. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00591 · Cited by 250
Sub-center ArcFace: Boosting Face Recognition by Large-Scale Noisy Web Faces
Deng, J., Guo, J., Liu, T., Gong, M., & Zafeiriou, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_43 · Cited by 247
“Compared to deep metric learning methods (e.g., Triplet [26], Tuplet [21,28]), margin-based softmax methods conduct global comparisons at the cost of memory consumption on holding the center of each class.”
BackgroundMethodInfluentialDeep Coupled ResNet for Low-Resolution Face Recognition
Lu, Z., Jiang, X., & Kot, A. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2810121 · Cited by 255
“While many FR approaches have been developed for recognizing highresolution (HR) face images [6]–[8], there are few studies focused on FR in surveillance systems, where HR cameras are not available or there is a long distance between the camera and the”
BackgroundLearning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval
Mithun, N. C., Li, J., Metze, F., & Roy-Chowdhury, A. K. (2018) · Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval · doi:10.1145/3206025.3206064 · Cited by 250
Ranked List Loss for Deep Metric Learning
Wang, X., Hua, Y., Kodirov, E., Hu, G., Garnier, R., & Robertson, N. M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00535 · Cited by 242
“Triplet-based losses are also widely studied [25, 35, 3].”
BackgroundMethodInfluentialMFDNet: Collaborative Poses Perception and Matrix Fisher Distribution for Head Pose Estimation
Liu, H., Fang, S., Zhang, Z., Li, D., Lin, K., & Wang, J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3081873 · Cited by 254
TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
Zhu, S., Shah, M., & Chen, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00123 · Cited by 241
“In a mini-batch with N streetview and aerial-view image pairs, we adopt the exhaustive strategy [20] to sample 2N(N − 1) triplets.”
MethodMulti-object Tracking with Quadruplet Convolutional Neural Networks
Son, J., Baek, M., Cho, M., & Han, B. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.403 · Cited by 247
“It has been used for feature learning [18, 26], unsupervised representation learning in videos [51], and face recognition [41] and person re-identifications [7].”
MethodRAM: A Region-Aware Deep Model for Vehicle Re-Identification
Liu, X., Zhang, S., Huang, Q., & Gao, W. (2018) · 2018 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486589 · Cited by 239
Monocular, One-stage, Regression of Multiple 3D People
Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M. J., & Mei, T. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01099 · Cited by 254
“To alleviate the ambiguity between embeddings of similar samples, associate embedding [38], triplet loss [44], and poseguided association [4] are developed for pose estimation, face recognition, and tracking respectively.”
MethodRetinaTrack: Online Single Stage Joint Detection and Tracking
Lu, Z., Rathod, V., Votel, R., & Huang, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01468 · Cited by 254
HyperExtended LightFace: A Facial Attribute Analysis Framework
Serengil, S. I., & Ozpinar, A. (2021) · 2021 International Conference on Engineering and Emerging Technologies (ICEET) · doi:10.1109/iceet53442.2021.9659697 · Cited by 233
CloudNet: Ground‐Based Cloud Classification With Deep Convolutional Neural Network
Zhang, J., Liu, P., Zhang, F., & Song, Q. (2018) · Geophysical Research Letters · doi:10.1029/2018gl077787 · Cited by 251
“In the past few years, convolutional neural networks (CNNs), which are a deep learning architecture, have achieved remarkable results in some fields, such as computer vision and pattern recognition (Schroff et al., 2015; Taigman et al., 2014).”
BackgroundAI Benchmark: All About Deep Learning on Smartphones in 2019
Ignatov, A., Timofte, R., Kulik, A., Yang, S., Wang, K., Baum, F., Wu, M., Xu, L., & Van Gool, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00447 · Cited by 247
“Among the most popular tasks are different computer vision problems like image classification [38, 82, 23], image enhancement [27, 28, 32, 30], image super-resolution [17, 42, 83], bokeh simulation [85], object tracking [87, 25], optical character recognition [56], face detection and recognition [44, 70], augmented re…”
BackgroundAdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
Zhang, X., Zhao, R., Qiao, Y., Wang, X., & Li, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01108 · Cited by 246
“A number of recent studies, such as DeepFace [36], DeepID2 [31], DeepID3 [32], VGGFace [25] and FaceNet [29], demon- strated that properly designed network architectures also lead to improved performance.”
BackgroundResultInfluentialPoint in, Box Out: Beyond Counting Persons in Crowds
Liu, Y., Shi, M., Zhao, Q., & Wang, X. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00663 · Cited by 239
“Meanwhile, knowing the person size and locations in a crowd at test stage is also very important; for example, in video surveilance, it enables person recognition [37], tracking [33], and re-identification [21].”
BackgroundFREE: Feature Refinement for Generalized Zero-Shot Learning
Chen, S., Wang, W., Xia, B., Peng, Q., You, X., Zheng, F., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00019 · Cited by 230
Deep Cascaded Bi-Network for Face Hallucination
Zhu, S., Liu, S., Loy, C. C., & Tang, X. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_37 · Cited by 237
“Meanwhile, facial analysis techniques, such as face alignment [2,3] and verification [4,5], have seen rapid progress.”
BackgroundGroup Consistent Similarity Learning via Deep CRF for Person Re-identification
Chen, D., Xu, D., Li, H., Sebe, N., & Wang, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00902 · Cited by 241
Triplet-Based Semantic Relation Learning for Aerial Remote Sensing Image Change Detection
Zhang, M., Xu, G., Chen, K., Yan, M., & Sun, X. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2869608 · Cited by 248
“In [9], the triplet loss function requires that the distance of the pair ( fw(x i j ), fw(x n i j )) is larger than that of the pair ( fw(x a i j ), fw(x p i j )) by a predefined margin.”
BackgroundMethodLearning to Remember Rare Events
Kaiser, Ł., Nachum, O., Roy, A., & Bengio, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.03129 · Cited by 218
How to Train Your Deep Multi-Object Tracker
Xu, Y., sep, A., Ban, Y., Horaud, R., Leal-Taixe, L., & Alameda-Pineda, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00682 · Cited by 232
“This external ReID module is a feature extractor network with a ResNet-50 backbone, trained using a triplet loss [44] on the MOTChallenge video sequences.”
BackgroundMethodInfluentialBiometrics recognition using deep learning: a survey
Minaee, S., Abdolrashidi, A., Su, H., Bennamoun, M., & Zhang, D. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10237-x · Cited by 245
“‖ ‖ In 2015, FaceNet Schroff et al. (2015) trained a GoogLeNet model on a large private dataset.”
MethodInfluentialSemantic Instance Segmentation for Autonomous Driving
De Brabandere, B., Neven, D., & Van Gool, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.66 · Cited by 246
Dynamic Graph Attention for Referring Expression Comprehension
Yang, S., Li, G., & Yu, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00474 · Cited by 233
“We adopt the triplet loss with online hard negative mining [23] to train the DGA network.”
MethodPose-Aware Face Recognition in the Wild
Masi, I., Rawls, S., Medioni, G., & Natarajan, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.523 · Cited by 240
“Regarding methods that trained a CNN to recognize faces, one approach to obtain pose-invariance is to train a single CNN with a large enough dataset covering a diverse set of poses so that the CNN in principle could learn some degree of pose invariance automatically: FaceNet [25] shows that it is possible to learn a c…”
BackgroundMethodTriplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning
Sirinam, P., Mathews, N., Rahman, M. S., & Wright, M. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3354217 · Cited by 231
“NSL has been broadly implemented in face recognition [24, 27], where it is a compelling approach due to constraints inherent in the task: Limited training data.”
BackgroundMethodResultInfluentialUMDFaces: An annotated face dataset for training deep networks
Bansal, A., Nanduri, A., Castillo, C. D., Ranjan, R., & Chellappa, R. (2017) · 2017 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/btas.2017.8272731 · Cited by 238
Vijay Kumar, B. G., Carneiro, G., & Reid, I. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.581 · Cited by 237
“However, sampling all possible pairs or triplets from the training dataset can quickly become intractable, where the majority of those samples may produce small costs in (3)-(5), resulting in slow convergence [26].”
BackgroundMethodInfluentialSixteen facial expressions occur in similar contexts worldwide
Cowen, A. S., Keltner, D., Schroff, F., Jou, B., Adam, H., & Prasad, G. (2021) · Nature · doi:10.1038/s41586-020-3037-7 · Cited by 240
Self-citationAttention-Based Ensemble for Deep Metric Learning
Kim, W., Goyal, B., Chawla, K., Lee, J., & Kwon, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_45 · Cited by 234
Dual Contrastive Prediction for Incomplete Multi-View Representation Learning
Lin, Y., Gou, Y., Liu, X., Bai, J., Lv, J., & Peng, X. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3197238 · Cited by 237
“In contrast, [50] has to exhaustively choose the hard negative pairs for guaranteeing performance.”
Not All Samples Are Created Equal: Deep Learning with Importance SamplingPreprint
Katharopoulos, A., & Fleuret, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00942 · Cited by 283
“On the other hand, for deep neural networks, sample selection methods were mainly employed to generate hard negative samples for embedding learning problems or to tackle the class imbalance problem (Schroff et al., 2015; Wu et al., 2017; Simo-Serra et al., 2015).”
BackgroundMethodSchneider, S., Taylor, G. W., Linquist, S., & Kremer, S. C. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13133 · Cited by 245
A principal odor map unifies diverse tasks in olfactory perception
Lee, B. K., Mayhew, E. J., Sanchez-Lengeling, B., Wei, J. N., Qian, W. W., Little, K. A., Andres, M., Nguyen, B. B., Moloy, T., Yasonik, J., et al. (2023) · Science · doi:10.1126/science.ade4401 · Cited by 240
Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
Meng, D., Li, L., Liu, X., Li, Y., Yang, S., Zha, Z.-J., Gao, X., Wang, S., & Huang, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00713 · Cited by 229
“215 Triplet[23] 0.”
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Liu, Z., Rodriguez-Opazo, C., Teney, D., & Gould, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00213 · Cited by 238
“Content-based Image Retrieval (CBIR) refers to the use of image-only queries for product search [26], face recognition [29, 34], etc.”
BackgroundLearning to Super-Resolve Blurry Face and Text Images
Xu, X., Sun, D., Pan, J., Zhang, Y., Pfister, H., & Yang, M.-H. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.36 · Cited by 235
“The loss function for D in (8) introduces the triplet loss [36] into the standard formulation of GAN to ensure that a real sample x is closer to another real sample x̂ than the generated one Gω(y).”
BackgroundCui, Y., Zhou, F., Lin, Y., & Belongie, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.130 · Cited by 234
“This section presents a bootstrapping framework on how to grow a small scale, fine-grained dataset in an efficient manner.”
BackgroundMethodLeveraging recent advances in deep learning for audio-Visual emotion recognition
Schoneveld, L., Othmani, A., & Abdelkawy, H. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.03.007 · Cited by 237
Face Recognition Systems Under Morphing Attacks: A Survey
Scherhag, U., Rathgeb, C., Merkle, J., Breithaupt, R., & Busch, C. (2019) · IEEE Access · doi:10.1109/access.2019.2899367 · Cited by 237
“standing field of research in which a major break-though has been achieved by the introduction of deep neural networks [3], [4].”
BackgroundVIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval
Zhu, S., Yang, T., & Chen, C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00364 · Cited by 230
“In a mini-batch with N groundview and aerial-view image pairs, we use the exhaustive strategy [15] to build 2N(N − 1) triplets, thereby making full use of all the input images.”
BackgroundMethodLearning Type-Aware Embeddings for Fashion Compatibility
Vasileva, M. I., Plummer, B. A., Dusad, K., Rajpal, S., Kumar, R., & Forsyth, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_24 · Cited by 222
Dense Classification and Implanting for Few-Shot Learning
Lifchitz, Y., Avrithis, Y., Picard, S., & Bursuc, A. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00948 · Cited by 216
“Traditional methods like siamese networks are also considered [3, 39, 18] along with models that learn by comparing multiple samples at once [43, 49, 41].”
MethodAttribute-Guided Face Generation Using Conditional CycleGAN
Lu, Y., Tai, Y.-W., & Tang, C.-K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01258-8_18 · Cited by 233
“Compared with another state-of-the-art FaceNet [15], which returns a 1792-”
BackgroundInfluentialLearned Contextual Feature Reweighting for Image Geo-Localization
Kim, H. J., Dunn, E., & Frahm, J.-M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.346 · Cited by 228
STA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification
Fu, Y., Wang, X., Wei, Y., & Huang, T. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018287 · Cited by 170
“The triplet loss with hard mining is first proposed in (Her-mans, Beyer, and Leibe 2017) as an improved version of the original semi-hard triplet loss (Schroff, Kalenichenko, and Philbin 2015).”
BackgroundMitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
Wang, M., & Deng, W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00934 · Cited by 222
Deep learning-based methods for person re-identification: A comprehensive review
Wu, D., Zheng, S.-J., Zhang, X.-P., Yuan, C.-A., Cheng, F., Zhao, Y., Lin, Y.-J., Zhao, Z.-Q., Jiang, Y.-L., & Huang, D.-S. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.079 · Cited by 229
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Chen, Y., Mancini, M., Zhu, X., & Akata, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3201576 · Cited by 220
Few-Shot Adaptive Gaze Estimation
Park, S., Mello, S. D., Molchanov, P., Iqbal, U., Hilliges, O., & Kautz, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00946 · Cited by 215
“The max function minimizes differences between intra-person features that are furthest apart, and is similar to the idea of batch-hard online triplet mining [35].”
MethodResultSER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
Terhorst, P., Kolf, J. N., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00569 · Cited by 221
Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
Liu, J., Deng, Y., Bai, T., Wei, Z., & Huang, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.07310 · Cited by 223
Recurrent convolutional structures for audio spoof and video deepfake detection
Chintha, A., Thai, B., Sohrawardi, S. J., Bhatt, K., Hickerson, A., Wright, M., & Ptucha, R. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2999185 · Cited by 226
“In a short paper, Sohrawardi et al. [33] described and very briefly evaluated models based on the FaceNet [50] CNN architecture, with weights initialized from the VGGFace2 [51] facial recognition task.”
MethodInfluentialTransductive Semi-Supervised Deep Learning Using Min-Max Features
Shi, W., Gong, Y., Ding, C., Ma, Z., Tao, X., & Zheng, N. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_19 · Cited by 215
“To date, Deep Convolutional Neural Networks (DCNNs) have shown state-of-the-art performances in numerous computer vision applications, such as image classification [1–5], object detection [6, 7], face recognition [8–10], image retrieval [11–14], etc.”
BackgroundDeep Ranking for Person Re-Identification via Joint Representation Learning
Chen, S.-Z., Guo, C.-C., & Lai, J.-H. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2545929 · Cited by 196
SegMap: Segment-based mapping and localization using data-driven descriptors
Dubé, R., Cramariuc, A., Dugas, D., Sommer, H., Dymczyk, M., Nieto, J., Siegwart, R., & Cadena, C. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364919863090 · Cited by 214
“In addition, we compare classificationbased learning with a triplet loss solution (Schroff et al., 2015), where during training, we enforce segments from the same sequence to have a minimal Euclidean distance.”
MethodHetero-Center loss for cross-modality person Re-identification
Zhu, Y., Yang, Z., Wang, L., Zhao, S., Hu, X., & Tao, D. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.100 · Cited by 222
Marginal Loss for Deep Face Recognition
Deng, J., Zhou, Y., & Zafeiriou, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.251 · Cited by 218
On the Reconstruction of Face Images from Deep Face Templates
Mai, G., Cao, K., Yuen, P. C., & Jain, A. K. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2827389 · Cited by 220
Deep Facial Diagnosis: Deep Transfer Learning From Face Recognition to Facial Diagnosis
Jin, B., Cruz, L., & Gonçalves, N. (2020) · IEEE Access · doi:10.1109/access.2020.3005687 · Cited by 221
“The CNN architectures [7], [8], [27] for face recognition including FaceNet, VGG-Face, DeepFace and ResNet get inspired from those architectures that perform well in ILSVRCs.”
MethodFacial Expression Recognition using Convolutional Neural Networks: State of the Art
Pramerdorfer, C., & Kampel, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.02903 · Cited by 211
“On the contrary, we postulate that modern deep networks can outperform the shallow architectures of current works, based on findings in related research fields [5], [6].”
BackgroundMethodInfluentialLearning Context Graph for Person Search
Yan, Y., Zhang, Q., Ni, B., Zhang, W., Xu, M., & Yang, X. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00226 · Cited by 209
“Some methods enable end-to-end feature and metric learning [1, 33, 8, 49, 56], other methods employ part information to build more robust representation [35, 23, 23, 23, 37, 40, 52, 44].”
MethodGe, W., Yang, S., & Yu, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00139 · Cited by 210
Detailed Human Avatars from Monocular Video
Alldieck, T., Magnor, M., Xu, W., Theobalt, C., & Pons-Moll, G. (2018) · 2018 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00022 · Cited by 206
‘Skimming-Perusal’ Tracking: A Framework for Real-Time and Robust Long-Term Tracking
Yan, B., Zhao, H., Wang, D., Lu, H., & Yang, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00247 · Cited by 218
“To ensure the efficiency of our tracking framework, we attempt to exploit an offline-trained verifier based on deep feature embedding [29].”
MethodLearning Compact Geometric Features
Khoury, M., Zhou, Q.-Y., & Koltun, V. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.26 · Cited by 214
“This objective has been used to optimize feature embeddings for a number of applications in computer vision [6, 28, 40].”
MethodStrengths and weaknesses of deep learning models for face recognition against image degradations
Grm, K., Štruc, V., Artiges, A., Caron, M., & Ekenel, H. K. (2018) · IET Biometrics · doi:10.1049/iet-bmt.2017.0083 · Cited by 216
“…deep learning-based face recognition focuses on new model architectures, better techniques for exploiting the generated face representations, and related approaches aimed at improving both the performance and robustness of deep face recognition technology on common benchmark tasks [37], [31], [27].”
BackgroundUV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition
Deng, J., Cheng, S., Xue, N., Zhou, Y., & Zafeiriou, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00741 · Cited by 214
Learning to Anonymize Faces for Privacy Preserving Action Detection
Ren, Z., Lee, Y. J., & Ryoo, M. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_38 · Cited by 215
Ring Loss: Convex Feature Normalization for Face Recognition
Zheng, Y., Pal, D. K., & Savvides, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00534 · Cited by 211
Face recognition: Past, present and future (a review)
Taskiran, M., Kahraman, N., & Erdem, C. E. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2020.102809 · Cited by 217
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
Chen, Y., Wang, N., & Zhang, Z. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11783 · Cited by 211
Shen, Z., Lai, W.-S., Xu, T., Kautz, J., & Yang, M.-H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00862 · Cited by 213
Audio-Visual Instance Discrimination with Cross-Modal Agreement
Morgado, P., Vasconcelos, N., & Misra, I. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01229 · Cited by 211
“While various loss functions have been defined for contrastive learning [57, 70], we focus on noise contrastive estimation (NCE) [23].”
BackgroundCaetano, C., Sena, J., Brémond, F., Santos, J. A. D., & Schwartz, W. R. (2019) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2019.8909840 · Cited by 254
“2Chain C considering 25 Kinect joints: [2, 21, 3, 4, 3, 21, 5, 6, 7, 8, 22, 23, 22, 8, 7, 6, 5, 21, 9, 10, 11, 12, 24, 25, 24, 12, 11, 10, 9, 21, 2, 1, 13, 14, 15, 16, 15, 14, 13, 1, 17, 18, 19, 20, 19, 18, 17, 1, 2], as defined in [34].”
BackgroundGaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set
Chao, H., Wang, K., He, Y., Zhang, J., & Feng, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3057879 · Cited by 212
DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge
Liu, R., Wang, X., Wu, Q., Dai, L., Fang, X., Yan, T., Son, J., Tang, S., Li, J., Gao, Z., et al. (2022) · Patterns · doi:10.1016/j.patter.2022.100512 · Cited by 211
Embedding Label Structures for Fine-Grained Feature Representation
Zhang, X., Zhou, F., Lin, Y., & Zhang, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.126 · Cited by 209
A deep active learning system for species identification and counting in camera trap images
Norouzzadeh, M. S., Morris, D., Beery, S., Joshi, N., Jojic, N., & Clune, J. (2021) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13504 · Cited by 214
Deep Over-sampling Framework for Classifying Imbalanced Data
Ando, S., & Huang, C. Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-71249-9_46 · Cited by 190
“Triplet loss re-sampling with cost-sensitive learning is a hybrid method that implements the triplet loss function used in [5,24,25] with re-sampling and cost-sensitive learning.”
MethodVehicle Re-Identification With Viewpoint-Aware Metric Learning
Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., & Wei, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00837 · Cited by 203
Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation
Ge, S., Zhao, S., Li, C., & Li, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2883743 · Cited by 209
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
Wang, S., Yu, L., Li, C., Fu, C.-W., & Heng, P.-A. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_10 · Cited by 187
MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems
Huang, T., Dong, Y., Ding, M., Yang, Z., Feng, W., Wang, X., & Tang, J. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467408 · Cited by 207
“Inspired by the efforts on metric learning [32, 34], we generalize the pairwise BPR loss to K-pair loss and study its effect on MixGCF.”
BackgroundMethodFace Model Compression by Distilling Knowledge from Neurons
Luo, P., Zhu, Z., Liu, Z., Wang, X., & Tang, X. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10449 · Cited by 199
SphereReID: Deep hypersphere manifold embedding for person re-identification
Fan, X., Jiang, W., Luo, H., & Fei, M. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.01.010 · Cited by 207
“Motivated by FaceNet [41], a convolutional neural network used to learn an embedding for faces, triplet loss [2] is used in [42,12] to optimize in the embedding space such that embedding features for the same identity are closer to each other than those of different identities.”
MethodThe Devil of Face Recognition Is in the Noise
Wang, F., Chen, L., Li, C., Huang, S., Chen, Y., Qian, C., & Loy, C. C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01240-3_47 · Cited by 201
Triplet probabilistic embedding for face verification and clustering
Sankaranarayanan, S., Alavi, A., Castillo, C. D., & Chellappa, R. (2016) · 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2016.7791205 · Cited by 164
A Multi-Task Deep Network for Person Re-Identification
Chen, W., Chen, X., Zhang, J., & Huang, K. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11201 · Cited by 198
Learning Causal Temporal Relation and Feature Discrimination for Anomaly Detection
Wu, P., & Liu, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3062192 · Cited by 203
“We use the cosine similarity to measure the similarity between two features, and it is expressed as follows: To implement the functionality discussed above, i.e., ANFs should be closer to NFs than AAFs in the feature space, we use the ranking loss [22].”
Method
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.