# Unsupervised Learning of Face Representations

arXiv: https://arxiv.org/abs/1803.01260 · HTML: https://mlsanity.com/paper/1803.01260/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2018.

## Built on by (most cited first, 4 of 4)

- [Learning Facial Representations from the Cycle-consistency of Face](https://mlsanity.com/paper/2108.03427/) (2021)
- [Pose-disentangled Contrastive Learning for Self-supervised Facial Representation](https://mlsanity.com/paper/2211.13490/) (2022)
- [VideoClusterNet: Self-Supervised and Adaptive Face Clustering For Videos](https://mlsanity.com/paper/2407.12214/) (2024)
- [Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification](https://mlsanity.com/paper/2411.19215/) (2024)

## Abstract (arXiv)

We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. We mine supervised training data by noting that multiple faces in the same video frame must belong to different persons and the same face tracked across multiple frames must belong to the same person. We obtain millions of face pairs from hundreds of videos without using any manual supervision. Although faces extracted from videos have a lower spatial resolution than those which are available as part of standard supervised face datasets such as LFW and CASIA-WebFace, the former represent a much more realistic setting, e.g. in surveillance scenarios where most of the faces detected are very small. We train our CNNs with the relatively low resolution faces extracted from video frames collected, and achieve a higher verification accuracy on the benchmark LFW dataset cf. hand-crafted features such as LBPs, and even surpasses the performance of state-of-the-art deep networks such as VGG-Face, when they are made to work with low resolution input images.