# Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

arXiv: https://arxiv.org/abs/1708.02191 · HTML: https://mlsanity.com/paper/1708.02191/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2017.

## Built on by (most cited first, 15 of 15)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Semantic-Aware Domain Generalized Segmentation](https://mlsanity.com/paper/2204.00822/) (2022)
- [Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning](https://mlsanity.com/paper/2105.07606/) (2021)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)
- [Federated Unsupervised Domain Adaptation for Face Recognition](https://mlsanity.com/paper/2204.04382/) (2022)
- [Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.09083/) (2023)
- [Domain adaptation in small-scale and heterogeneous biological datasets](https://mlsanity.com/paper/2405.19221/) (2024)
- [Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionary](https://mlsanity.com/paper/2103.02250/) (2021)
- [Deep face recognition with clustering based domain adaptation](https://mlsanity.com/paper/2205.13937/) (2022)
- [Goldilocks Test Sets for Face Verification](https://mlsanity.com/paper/2405.15965/) (2024)
- [Domain Adapting Ability of Self-Supervised Learning for Face Recognition](https://mlsanity.com/paper/2102.13319/) (2021)
- [Mitigating Domain Mismatch in Face Recognition Using Style Matching](https://mlsanity.com/paper/2102.13327/) (2021)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [Adaptive Face Recognition Using Adversarial Information Network](https://mlsanity.com/paper/2305.13605/) (2023)
- [Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation](https://mlsanity.com/paper/2601.03718/) (2026)

## Abstract (arXiv)

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.