The DOI matches its Crossref record; 49 of the 50 references it cites were found in a registry or an index.
Feature Transfer Learning for Face Recognition With Under-Represented Data
Abstract
Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data. Training with under-represented data leads to biased classifiers in conventionally-trained deep networks. In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples. A Gaussian prior of the variance is assumed across all subjects and the variance from regular ones are transferred to the under-represented ones. This encourages the under-represented distribution to be closer to the regular distribution. Further, an alternating training regimen is proposed to simultaneously achieve less biased classifiers and a more discriminative feature representation. We conduct ablative study to mimic the under-represented datasets by varying the portion of under-represented classes on the MS-Celeb-1M dataset. Advantageous results on LFW, IJB-A and MS-Celeb-1M demonstrate the effectiveness of our feature transfer and training strategy, compared to both general baselines and state-of-the-art methods. Moreover, our feature transfer successfully presents smooth visual interpolation, which conducts disentanglement to preserve identity of a class while augmenting its feature space with non-identity variations such as pose and lighting.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“When the data has a long-tail distribution, it can lead to bias in the classifier.”
From An Improved VGG19 Transfer Learning Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets (2021) · cites this paper as [4]
In the citing paper
“The classifier is more inclined to identify classes with a sufficient sample size and rich diversity [4,5].”
From An Improved VGG19 Transfer Learning Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets (2021) · cites this paper as [4]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359
Flagged first, then by citations
1 of the 50 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- van der maaten, 2008, Visualizing high-dimensional data using t-SNE, Journal of Machine Learning Research, 9, 2579
- lecun, 1998, The MNIST database of handwritten digits, Technical Report
- wang, 2017, NormFace L2 Hypersphere Embedding for Face Verification
- horn, 2017, The devial is in the tails Finegrained classification in the wild
- 10.1109/FG.2017.11 · DOI
Cited by
Sorted by citations
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
Class-Balanced Loss Based on Effective Number of Samples
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., & Belongie, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00949 · Cited by 3,094
Deep face recognition: A survey
Wang, M., & Deng, W. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.10.081 · Cited by 1,268
Decoupling Representation and Classifier for Long-Tailed RecognitionPreprint
Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., & Kalantidis, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.09217 · Cited by 1,217
“variance (Yin et al., 2019) and transferring semantic deep features (Liu et al.”
BackgroundDeep Long-Tailed Learning: A Survey
Zhang, Y., Kang, B., Hooi, B., Yan, S., & Feng, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268118 · Cited by 924
Past, Present, and Future of Face Recognition: A Review
Adjabi, I., Ouahabi, A., Benzaoui, A., & Ahmed, A. T. (2020) · Electronics · doi:10.3390/electronics9081188 · Cited by 640
Equalization Loss for Long-Tailed Object Recognition
Tan, J., Wang, C., Li, B., Li, Q., Ouyang, W., Yin, C., & Yan, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01168 · Cited by 528
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 518
Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
Liu, Y., Ao, X., Qin, Z., Chi, J., Feng, J., Yang, H., & He, Q. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449989 · Cited by 536
“Other approaches like transfer learning [45], metric learning [46] could also be used to resolve the class imbalance problem.”
BackgroundA Review of Face Recognition Technology
Li, L., Mu, X., Li, S., & Peng, H. (2020) · IEEE Access · doi:10.1109/access.2020.3011028 · Cited by 421
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
Wei, C., Sohn, K., Mellina, C., Yuille, A., & Yang, F. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01071 · Cited by 313
Self-citationRethinking the Value of Labels for Improving Class-Imbalanced LearningPreprint
Yang, Y., & Xu, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07529 · Cited by 320
“Other learning paradigms, including transfer learning [33, 54], metric learning [55, 58], and meta-learning [1, 45], have also been explored.”
BackgroundFeature Space Augmentation for Long-Tailed Data
Chu, P., Bian, X., Liu, S., & Ling, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58526-6_41 · Cited by 272
Jamal, M. A., Brown, M., Yang, M., Wang, L., & Gong, B. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00763 · Cited by 270
Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective
Liu, J., Sun, Y., Han, C., Dou, Z., & Li, W. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00304 · Cited by 244
“First, like the previous works [41, 46], we assign a label to mark the head and tail class, yielding the vanilla version.”
BackgroundMethodIntelligent financial fraud detection practices in post-pandemic era
Zhu, X., Ao, X., Qin, Z., Chang, Y., Liu, Y., He, Q., & Li, J. (2021) · The Innovation · doi:10.1016/j.xinn.2021.100176 · Cited by 238
“The class imbalance problem on feature-based neural methods has been studied in depth, such as re-sampling, re-weighting, and transfer learning.(95,169) Whereas in the GNNs works, the noisy information, few interactions among fraudsters, and desalination of the minority class’s features caused by the message aggregati…”
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
Tan, J., Lu, X., Zhang, G., Yin, C., & Li, Q. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00173 · Cited by 210
“[6, 43] augment the under-represented classes in the feature space by using the knowledge learned from head classes.”
BackgroundMetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Li, S., Gong, K., Liu, C. H., Wang, Y., Qiao, F., & Cheng, X. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00517 · Cited by 186
Towards Universal Representation Learning for Deep Face Recognition
Shi, Y., Yu, X., Sohn, K., Chandraker, M. K., & Jain, A. K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00685 · Cited by 180
Self-citationImage Enhancement for Tuberculosis Detection Using Deep Learning
Munadi, K., Muchtar, K., Maulina, N., & Pradhan, B. (2020) · IEEE Access · doi:10.1109/access.2020.3041867 · Cited by 179
“tion [3], [4], autonomous cars [5], vehicle classification [6], and many others [7]–[9], [50].”
BackgroundRegularizing Deep Networks with Semantic Data Augmentation
Wang, Y., Huang, G. M., Song, S., Pan, X., Xia, Y., & Wu, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3052951 · Cited by 174
Long- Tailed Recognition via Weight Balancing
Alshammari, S., Wang, Y.-X., Ramanan, D., & Kong, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00677 · Cited by 169
“Transfer learning methods transfer feature representations learned on the common-classes to the rare-classes [48, 79].”
BackgroundClassical and modern face recognition approaches: a complete review
Ali, W., Tian, W., Din, S. U., Iradukunda, D., & Khan, A. A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09850-1 · Cited by 170
The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances
Du, H., Shi, H., Zeng, D., Zhang, X.-P. S., & Mei, T. (2022) · ACM Computing Surveys · doi:10.1145/3507902 · Cited by 172
“[292], Video-based Performing face recognition with video sequences.”
BackgroundMethodA Comprehensive Study on Face Recognition Biases Beyond Demographics
Terhörst, P., Kolf, J. N., Huber, M., Kirchbuchner, F., Damer, N., Morales, A., Fiérrez, J., & Kuijper, A. (2021) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2021.3111823 · Cited by 167
Jain, A. K., Deb, D., & Engelsma, J. J. (2021) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2021.3115465 · Cited by 158
SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
Zhong, Y., Deng, W., Hu, J., Zhao, D., Li, X., & Wen, D. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048632 · Cited by 144
“are a significant portion of under-represented identities [24], [25], [26], [27].”
BackgroundFASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
Zang, Y., Huang, C., & Loy, C. C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00344 · Cited by 135
“The feature augmentation methods already show benefits for face recognition [44, 26], person Re-ID [26] and classification [20, 6].”
BackgroundMethodInfluentialJointly De-Biasing Face Recognition and Demographic Attribute Estimation
Gong, S., Liu, X., & Jain, A. K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58526-6_20 · Cited by 141
“ution. Range Loss [57] learns a robust face representation that makes the most use of every training sample. To mitigate the impact of insucient class samples, center-based feature transfer learning [55] and large margin feature augmentation [52] are proposed to augment features of minority identities and equalize cla…”
BackgroundSelf-citationFace Recognition: Too Bias, or Not Too Bias?
Robinson, J. P., Livitz, G., Henon, Y., Qin, C., Fu, Y., & Timoner, S. J. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00008 · Cited by 134
Fidora: Robust WiFi-Based Indoor Localization via Unsupervised Domain Adaptation
Chen, X., Li, H., Zhou, C., Liu, X., Wu, D., & Dudek, G. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3163391 · Cited by 132
Self-citationRSG: A Simple but Effective Module for Learning Imbalanced Datasets
Wang, J., Lukasiewicz, T., Hu, X., Cai, J., & Xu, Z. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00378 · Cited by 114
Self Supervision to Distillation for Long-Tailed Visual Recognition
Li, T., Wang, L., & Wu, G. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00067 · Cited by 106
“In addition, researchers tackled long-tailed recognition by transferring knowledge from head classes to tail classes [28, 49, 46, 20, 48].”
BackgroundMethodImbalanced Continual Learning with Partitioning Reservoir Sampling
Kim, C. D., Jeong, J., & Kim, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58601-0_25 · Cited by 101
Wan, X., Zhang, X., & Liu, L. (2021) · Applied Sciences · doi:10.3390/app11062606 · Cited by 90
“The classi‐ fier is more inclined to identify classes with a sufficient sample size and rich diversity [4,5].”
BackgroundBalanced knowledge distillation for long-tailed learning
Zhang, S., Chen, C., Hu, X., & Peng, S. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.01.063 · Cited by 97
SecureFace: Face Template Protection
Mai, G., Cao, K., Lan, X., & Yuen, P. C. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3009590 · Cited by 80
Deep learning based single sample face recognition: a survey
Liu, F., Chen, D., Wang, F., Li, Z., & Xu, F. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10240-2 · Cited by 80
Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a Class-Imbalance View
Guo, Y., Nie, L., Cheng, Z., Tian, Q., & Zhang, M. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3128322 · Cited by 83
“The knowledge can be intra-class variance [45] or deep semantic features [46].”
BackgroundAdaptive Logit Adjustment Loss for Long-Tailed Visual Recognition
Zhao, Y. L., Chen, W., Tan, X., Huang, K., & Zhu, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20258 · Cited by 81
“2017), knowledge transferring (Yin et al. 2019; Liu et al. 2019) and network structure designing (Kang et al.”
BackgroundInfluentialOn Soft-Biometric Information Stored in Biometric Face Embeddings
Terhörst, P., Fährmann, D., Damer, N., Kirchbuchner, F., & Kuijper, A. (2021) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2021.3093920 · Cited by 74
Chen, B., Liu, K., Xu, Y., Wu, Q., & Yao, J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3141616 · Cited by 78
“For instance, feature transfer learning [39] and the implicit semantic data augmentation (ISDA) algorithm [40] explicitly and implicitly augment the under-represented data in the feature space.”
BackgroundWu, J., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2021) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2021.107934 · Cited by 71
Yücer, Ş., Akçay, S., Al-Moubayed, N., & Breckon, T. P. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00017 · Cited by 70
“Feature transformation is another pre-processing approach [34] that improves the feature space of under-represented subjects by moving the distribution of the feature space closer to the regular, supposedly unbiased distribution.”
BackgroundFiDo: Ubiquitous Fine-Grained WiFi-based Localization for Unlabelled Users via Domain Adaptation
Chen, X., Li, H., Zhou, C., Liu, X., Wu, D., & Dudek, G. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380091 · Cited by 74
“Besides indoor localization, transfer learning has also been applied to many other tasks, including object recognition [10], face recognition [48], electricity load forecasting [43], item ranking [13] and disease forecasting [52].”
Self-citationFaster Meta Update Strategy for Noise-Robust Deep Learning
Xu, Y., Zhu, L., Jiang, L., & Yang, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00021 · Cited by 68
“Long-tailed recognition has been an active research field in computer vision [3, 7, 10, 42, 32, 57, 30, 21, 6, 2, 16, 63, 64].”
BackgroundMethodMFCosface: A Masked-Face Recognition Algorithm Based on Large Margin Cosine Loss
Deng, H., Feng, Z., Qian, G., Lv, X., Li, H., & Li, G. (2021) · Applied Sciences · doi:10.3390/app11167310 · Cited by 70
“affects the extraction of facial features [3,4], leading to low recognition accuracy, so the algorithm research on masked-face recognition has great practical significance at the moment [5].”
BackgroundPost-comparison mitigation of demographic bias in face recognition using fair score normalization
Terhörst, P., Kolf, J. N., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.11.007 · Cited by 64
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Tian, C., Wang, W., Zhu, X., Dai, J., & Qiao, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19806-9_5 · Cited by 65
ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised LearningPreprint
Lee, H., Shin, S., & Kim, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.10368 · Cited by 57
Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
Li, M., Hu, Z., Lu, Y., Lan, W., Cheung, Y., & Huang, H. F. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i12.29262 · Cited by 58
Identifying and Compensating for Feature Deviation in Imbalanced Deep LearningPreprint
Ye, H.-J., Chen, H.-Y., Zhan, D., & Chao, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01385 · Cited by 98
“[15, 28, 59] found that the learned linear classifiers of a ConvNet tend to have larger norms for the major classes and proposed to either force similar norms in training or calibrate the norms in testing.”
BackgroundResultInvariant Feature Learning for Generalized Long-Tailed Classification
Tang, K., Tao, M., Qi, J., Liu, Z., & Zhang, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20053-3_41 · Cited by 53
Terhörst, P., Kolf, J. N., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304865 · Cited by 49
“[56] proposed a center-based feature transfer framework to augment under-represented samples.”
BackgroundClass-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition
Zhou, Z., Li, L., Zhao, P., Heng, P., & Gong, W. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00341 · Cited by 47
“In computer vision, numerous deep long-tailed learning studies have emerged in recent years, which mainly belong to 5 categories: class rebalancing [7, 10, 28, 40, 45, 52, 54], information augmentation [22,27,31,50,55], decoupled training [20,58,62], representation learning [9, 32, 51, 59, 65] and ensemble learning [6…”
BackgroundPIDray: A Large-Scale X-ray Benchmark for Real-World Prohibited Item Detection
Zhang, L., Jiang, L., Ji, R., & Fan, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01855-1 · Cited by 54
“For example, Feature Transfer Learning (Yin et al., 2019) proposes to leverage class information in the head to perform feature amplification on those in the tail.”
BackgroundCurvature-Balanced Feature Manifold Learning for Long-Tailed Classification
Ma, Y., Jiao, L., Liu, F., Yang, S., Liu, X., & Li, L. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01519 · Cited by 48
“, class re-balancing [8,14, 24, 34, 37, 46, 52], information augmentation [23, 31, 35, 38, 39,44,56,64,67], decoupled training [10,16,29,30,71,76], and ensemble learning [20, 36, 57, 58, 61, 72, 77] have been proposed to improve the performance of tail classes.”
Self-citationFAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization
Yin, X. P., Tai, Y. Y., Huang, Y., & Liu, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_19 · Cited by 45
Self-citationClass-Balancing Diffusion Models
Qin, Y., Zheng, H., Yao, J., Zhou, M., & Zhang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01768 · Cited by 53
“There mainly exist three paradigms in this domain, namely Class Re-balancing [29,31], Information Augmentation [26,49,52] and Module Improvement [16, 34].”
BackgroundMethodMemory-Based Jitter: Improving Visual Recognition on Long-Tailed Data with Diversity in Memory
Liu, J., Li, W., & Sun, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20064 · Cited by 49
A survey of class-imbalanced semi-supervised learning
Gui, Q., Hong, Z., Guo, N., & Niu, B. (2023) · Machine Learning · doi:10.1007/s10994-023-06344-7 · Cited by 51
“Yin et al. (2019) trained less biased classifiers by leveraging the knowledge of intra-class variance from head-classes to tail-classes, adapting the feature distribution of tail-classes to mimic that of head-classes.”
InfluentialLong-Tailed Class Incremental Learning
Liu, X., Hu, Y., Cao, X., Bagdanov, A. D., Li, K., & Cheng, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19827-4_29 · Cited by 45
Self-citationBeyond Identity: What Information Is Stored in Biometric Face Templates?
Terhörst, P., Fährmann, D., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304874 · Cited by 42
“Since the knowledge about encoded attributes in face template is required to develop more advanced biasmitigating solutions [7, 21, 38, 39] and more comprehensive privacy-enhancing technologies, in this work we investigate the predictability of 113 attributes from face templates at different difficulty-levels.”
BackgroundExploring Vision-Language Models for Imbalanced Learning
Wang, Y., Yu, Z., Wang, J., Heng, Q., Chen, H., Ye, W., Xie, R., Xie, X., & Zhang, S. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01868-w · Cited by 40
“…paradigms include task-specific architecture design (Wang et al., 2021c; Zhou et al., 2020; Wang et al., 2021a), transfer learning (Liu et al., 2019; Yin et al., 2019), domain adaptation (Jamal et al., 2020), semi-supervised learning, and self-supervised learning (Yang and Xu, 2020) which demand…”
Comparison-Level Mitigation of Ethnic Bias in Face Recognition
Terhörst, P., Tran, M. L., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf49977.2020.9107956 · Cited by 38
“Kortylewski et al. [20] proposed a data augmentation approach with synthetic data generation and Yin et al. [35] proposed a center-based feature transfer framework to augment under-represented samples.”
BackgroundSelf-supervised ECG pre-training
Liu, H., Zhao, Z., & She, Q. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103010 · Cited by 39
Zhang, X., Chen, Z., Gao, J., Huang, W., Li, P., & Zhang, J. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.108060 · Cited by 40
Wang, P., Zhao, Z., Su, F., & Meng, H. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3179902 · Cited by 37
“Finally, for data generation methods [55]–[58], additional fake samples or features are synthesized by generative models to equilibrate long-tailed distributions.”
MethodNoise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
Stehouwer, J., Jourabloo, A., Liu, Y., & Liu, X. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00732 · Cited by 37
Self-citationDropLoss for Long-Tail Instance Segmentation
Hsieh, T.-I., Robb, E., Chen, H.-T., & Huang, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16246 · Cited by 39
Pose-invariant face recognition with multitask cascade networks
Elharrouss, O., Almaadeed, N., Al-Maadeed, S. A., & Khelifi, F. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06690-4 · Cited by 39
Yang, G., Chen, G., Li, C., Fu, J., Guo, Y., & Hua, L. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.671134 · Cited by 37
“With transfer learning, major category samples andminor category samples are modeled separately, and the learned informativeness, representation, and knowledge of major category samples are transferred to minor category use (Liu et al., 2019; Yin et al., 2019).”
BackgroundThe Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Tan, J., Li, B., Lu, X., Yao, Y., Yu, F., He, T., & Ouyang, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3298433 · Cited by 37
“Recently, other works address the long-tailed problem from different perspectives such as transfer learning [5], [33], [34], supervised contrastive learning [35], [36], [37], [38], ensemble learning [39], [40], [41], [42], [43], and so on.”
BackgroundDeeper Exercise Monitoring for Smart Gym using Fused RFID and CV Data
Liu, Z., Liu, X., & Li, K. (2020) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom41043.2020.9155360 · Cited by 33
Self-citationOrthogonality Loss: Learning Discriminative Representations for Face Recognition
Yang, S., Deng, W., Wang, M., Du, J., & Hu, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3021128 · Cited by 33
Ma, Y., Jiao, L., Liu, F., Yang, S., Liu, X., & Chen, P. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3303697 · Cited by 32
Self-citationMS-ALN: Multiscale Attention Learning Network for Pest Recognition
Feng, F., Dong, H., Zhang, Y., Zhang, Y., & Li, B. (2022) · IEEE Access · doi:10.1109/access.2022.3167397 · Cited by 34
“In addition, other methods such as fine-tuning [30], meta-learning [31] and knowledge transfer learning [32], [33], etc. are popular for long-tailed distributions.”
MethodBoosting Knowledge Distillation via Intra-Class Logit Distribution Smoothing
Li, C., Cheng, G., & Han, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3327113 · Cited by 33
“(i) Class-imbalance learning: [82] and [83] augmented the feature space of the tail classes to enlarge the intra-class variance, mitigating the bias decision boundary problem and eventually prompting the performance in long-tail learning.”
BackgroundDelving into the Trajectory Long-tail Distribution for Muti-object Tracking
Chen, S., Yu, E., Li, J., & Tao, W. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01830 · Cited by 33
Hierarchical Memory Learning for Fine-Grained Scene Graph Generation
Deng, Y., Li, Y., Zhang, Y., Xiang, X., Wang, J., Chen, J., & Ma, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19812-0_16 · Cited by 32
“[30,55] proposed a guiding feature in the head to augment tail learning.”
BackgroundCamera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning
Ahmed, S. M., Lejbølle, A. R., Panda, R., & Roy–Chowdhury, A. K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01216 · Cited by 31
Semi-Siamese Training for Shallow Face Learning
Du, H., Shi, H., Liu, Y., Wang, J., Lei, Z., Zeng, D., & Mei, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58548-8_3 · Cited by 30
Deep Generative Mixture Model for Robust Imbalance Classification
Wang, X., Jing, L., Lyu, Y., Guo, M., Wang, J., Liu, H., Yu, J. J., & Zeng, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3178914 · Cited by 30
“To generate diverse samples, inspired by [46], we adapt the latent feature distribution of tail classes by enlarging the intra-class variance.”
BackgroundMethodAn Automated Biometric Identification System Using CNN-Based Palm Vein Recognition
Jhong, S.-Y., Tseng, P.-Y., Siriphockpirom, N., Hsia, C.-H., Huang, M.-S., Hua, K.-L., & Chen, Y.-Y. (2020) · 2020 International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris50834.2020.9205778 · Cited by 31
“Many biometric methods have been proposed, such as face recognition [1], fingerprint recognition [2], palm print recognition [3], iris recognition [4] and palm vein recognition [5].”
BackgroundBoosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
Shi, S., Qiao, K., Yang, S., Wang, L., Chen, J., & Yan, B. (2021) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.775688 · Cited by 33
“Themethod based on transfer learning solves the problem by transferring the characteristics learned from majority classes to minority classes (Yin et al., 2019).”
BackgroundImproved Wafer Map Inspection Using Attention Mechanism and Cosine Normalization
Xu, Q., Yu, N., & Essaf, F. (2022) · Machines · doi:10.3390/machines10020146 · Cited by 31
Bazzi, H., Ienco, D., Baghdadi, N. N., Zribi, M., & Demarez, V. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2960625 · Cited by 28
“In the general context of fine-tuning approaches [11], [13], the model learned on the source data is directly fine-tuned on the target data without considering the issues related to scarce or limited information.”
BackgroundRecognizing Characters in Art History Using Deep Learning
Madhu, P., Kosti, R., Mührenberg, L., Bell, P. R. F., Maier, A., & Christlein, V. (2019) · Workshop on Structuring and Understanding of Multimedia heritAge Contents (SUMAC) · doi:10.1145/3347317.3357242 · Cited by 27
“cratch, the available face data is insufficient in comparison. Transfer learning is a method where the knowledge learned in one domain can be carefully transferred to another, which can be beneficial [35, 47]. Typically, the new domain to be adapted for transfer learning must have a similar feature space and data dist…”
BackgroundResearch on Transfer Learning of Vision-based Gesture Recognition
Wu, B., Yang, C., & Zhong, J. (2021) · Machine Intelligence Research · doi:10.1007/s11633-020-1273-9 · Cited by 28
Procrustean Training for Imbalanced Deep Learning
Ye, H.-J., Zhan, D., & Chao, W. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00016 · Cited by 30
Du, J., Zhang, X., Liu, P., Vong, C., & Wang, T. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3286484 · Cited by 27
“These classes with dense data distribution are also easily misclassified [22], [23].”
BackgroundCross-Domain Similarity Learning for Face Recognition in Unseen Domains
Faraki, M., Yu, X., Tsai, Y., Suh, Y., & Chandraker, M. K. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01504 · Cited by 26
“Efforts in addressing unseen scenarios are either on transferring existing class variances to under-represented classes [47], or learning universal features through various augmentations [37].”
BackgroundSelf-citationLabel-Noise Learning with Intrinsically Long-Tailed Data
Lu, Y., Zhang, Y., Han, B., Cheung, Y., & Wang, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00132 · Cited by 29
“Methods such as FTL [56], RIDE [46] and DiVE [15] try to solve the problem by using the idea of transfer learning.”
MethodDual layer transfer learning for sEMG-based user-independent gesture recognition
Zhang, Y., Chen, Y., Yu, H., Yang, X., & Wang, L. (2020) · Personal and Ubiquitous Computing · doi:10.1007/s00779-020-01397-0 · Cited by 26
A knowledge-guide hierarchical learning method for long-tailed image classification
Chen, Q., Liu, Q., & Lin, E. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.008 · Cited by 24
Dynamic Training Data Dropout for Robust Deep Face Recognition
Zhong, Y., Deng, W., Fang, H., Hu, J., Zhao, D., Li, X., & Wen, D. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3123478 · Cited by 25
Zhao, W., & Zhao, H. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109842 · Cited by 23
Imbalanced data-oriented model learning method for ultra-short-term air conditioning load prediction
Tian, Z., Lin, X., Lu, Y., Song, W., & Niu, J. (2023) · Energy and Buildings · doi:10.1016/j.enbuild.2023.112931 · Cited by 24
Learning to Learn across Diverse Data Biases in Deep Face Recognition
Liu, C., Yu, X., Tsai, Y., Faraki, M., Moslemi, R., Chandraker, M. K., & Fu, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00404 · Cited by 25
“To adaptively learn the sampling, recent methods exploit hard negative mining [7, 24], metric learning [18, 26, 34, 35, 59, 61, 62] and meta learning [15, 21, 37, 55].”
MethodSelf-citationDebFace: De-biasing Face RecognitionPreprint
Gong, S., Liu, X., & Jain, A. K. (2019) · arXiv (Cornell University) · Cited by 24
Self-citation
Metadata
- Authors
- Yin, X., Yu, X., Sohn, K., Liu, X., & Chandraker, M.
- Affiliations
- Microsoft (United States) (US)
- NEC (Japan) (JP)
- NEC (United States) (US)
- Michigan State University (US)
- University of California San Diego (US)
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 5697-5706
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2962895364
- Cited by
- 346
- References
- 50
- Citations by year
- 2026: 7 · 2025: 28 · 2024: 63 · 2023: 67 · 2022: 57 · 2021: 69 · 2020: 49 · 2019: 6
- FWCI
- 14.75
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- 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
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- face recognition, underrepresented classes, classifier bias, alternating training, feature space augmentation, disentangled representations
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
