# SSDL: Self-Supervised Domain Learning for Improved Face Recognition

arXiv: https://arxiv.org/abs/2011.13361 · HTML: https://mlsanity.com/paper/2011.13361/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc. An individual's face appearance can vary drastically under different conditions creating a gap between train (source) and varying test (target) data. The domain gap could cause decreased performance levels in direct knowledge transfer from source to target. Despite fine-tuning with domain specific data could be an effective solution, collecting and annotating data for all domains is extremely expensive. To this end, we propose a self-supervised domain learning (SSDL) scheme that trains on triplets mined from unlabelled data. A key factor in effective discriminative learning, is selecting informative triplets. Building on most confident predictions, we follow an "easy-to-hard" scheme of alternate triplet mining and self-learning. Comprehensive experiments on four different benchmarks show that SSDL generalizes well on different domains.