Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the difficulty of curating diverse large-scale video datasets. This paper addresses both of those challenges, through an image to video feature-level domain adaptation approach, to learn discriminative video frame representations. The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative knowledge from large-scale labeled still images. Given a face recognition network that is pretrained in the image domain, the adaptation is achieved by (i) distilling knowledge from the network to a video adaptation network through feature matching, (ii) performing feature restoration through synthetic data augmentation and (iii) learning a domain-invariant feature through a domain adversarial discriminator. We further improve performance through a discriminator-guided feature fusion that boosts high-quality frames while eliminating those degraded by video domain-specific factors. Experiments on the YouTube Faces and IJB-A datasets demonstrate that each module contributes to our feature-level domain adaptation framework and substantially improves video face recognition performance to achieve state-of-the-art accuracy. We demonstrate qualitatively that the network learns to suppress diverse artifacts in videos such as pose, illumination or occlusion without being explicitly trained for them.
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.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
A Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077 · cited 2×
“50 CenterFace [36] 94.”
Learning a Similarity Metric Discriminatively, with Application to Face Verification
Chopra, S., Hadsell, R., & LeCun, Y. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.202 · Cited by 4,036
Adapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 1×
“The basic idea of feature space alignment is to minimize the distance between domains in the feature space through learning a transformation of source to target features [8, 25, 7, 35, 43], or a joint adaptation layer that embeds features into a new domain-invariant space [22, 33].”
BackgroundDeep domain confusion Maximizing for domain invariance
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014) · arXiv · doi:10.48550/arxiv.1412.3474 · Cited by 2,285
Transfer Feature Learning with Joint Distribution Adaptation
Long, M., Wang, J., Ding, G., Sun, J., & Yu, P. S. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.274 · Cited by 2,071
Return of Frustratingly Easy Domain Adaptation
Sun, B., Feng, J., & Saenko, K. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10306 · Cited by 2,004 · cited 4×
“We study the effectiveness of our proposed method in comparison to other works on unsupervised domain adaptation such as PCA feature transform or Correlation Alignment (CORAL) [28] methods.”
MethodInfluentialReturn of Frustratingly Easy Domain Adaptation
Sun, B., Feng, J., & Saenko, K. (2015) · arXiv · doi:10.48550/arxiv.1511.05547 · Cited by 2,004
Cited by
VGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
Deep visual domain adaptation: A survey
Wang, M., & Deng, W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.083 · Cited by 2,209
Deep face recognition: A survey
Wang, M., & Deng, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.081 · Cited by 1,466
Learning to Adapt Structured Output Space for Semantic Segmentation
Tsai, Y.-H., Hung, W.-C., Schulter, S., Sohn, K., Yang, M.-H., & Chandraker, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00780 · Cited by 1,430
Self-citationA Light CNN for Deep Face Representation With Noisy Labels
Wu, X., He, R., Sun, Z., & Tan, T. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2833032 · Cited by 1,186
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
Synthetic Data for Deep Learning
Nikolenko, S. I. (2021) · Springer Optimization and Its Applications · doi:10.1007/978-3-030-75178-4 · Cited by 423
Racial faces in the wild: Reducing racial bias by information maximization adaptation network
Wang, M., Deng, W., Hu, J., Tao, X., & Huang, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00078 · Cited by 353
“Sohn et al. [57] synthesized video frames from images by a set of transformations and applied a domain adversarial discriminator to align feature space of image and video domains.”
MethodFeature Transfer Learning for Face Recognition With Under-Represented Data
Yin, X., Yu, X., Sohn, K., Liu, X., & Chandraker, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00585 · Cited by 346
Self-citationDomain Adaptation for Structured Output via Discriminative Patch Representations
Tsai, Y.-H., Sohn, K., Schulter, S., & Chandraker, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00154 · Cited by 323
Self-citationConditional Generative Adversarial Network for Structured Domain Adaptation
Hong, W., Wang, Z., Yang, M., & Yuan, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00145 · Cited by 309
Self-citationGradually Vanishing Bridge for Adversarial Domain Adaptation
Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., & Tian, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01247 · Cited by 276
Authorship Attribution of Social Media Messages
Theophilo, A., Giot, R., & Rocha, A. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3123895 · Cited by 25
“Similar to what is done with images [46] and videos [47], this strategy can also work as a regularizer, avoiding noisy undesired features, forcing the model to pay attention to the desired patterns, and boosting the model performance with more training data.”
Result
Metadata
- Authors
- Sohn, K., Liu, S., Zhong, G., Yu, X., Yang, M.-H., & Chandraker, M.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 5917-5925
- OpenAlex
- W2743242403
- Cited by
- 110
- References
- 12
- FWCI
- 5.18
- Type
- conference paper
- Language
- en
- Open access
- green
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.