# Exploring Unlabeled Faces for Novel Attribute Discovery

arXiv: https://arxiv.org/abs/1912.03085 · HTML: https://mlsanity.com/paper/1912.03085/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [A Style-aware Discriminator for Controllable Image Translation](https://mlsanity.com/paper/2203.15375/) (2022)
- [MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance](https://mlsanity.com/paper/2504.13211/) (2025)
- [Disentangled Face Attribute Editing via Instance-Aware Latent Space Search](https://mlsanity.com/paper/2105.12660/) (2021)
- [Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2105.03117/) (2021)
- [DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation](https://mlsanity.com/paper/2209.06357/) (2022)
- [LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data](https://mlsanity.com/paper/2208.14889/) (2022)
- [Stay Positive: Non-Negative Image Synthesis for Augmented Reality](https://mlsanity.com/paper/2202.00659/) (2022)
- [MFIM: Megapixel Facial Identity Manipulation](https://mlsanity.com/paper/2308.01536/) (2023)

## Abstract (arXiv)

Despite remarkable success in unpaired image-to-image translation, existing systems still require a large amount of labeled images. This is a bottleneck for their real-world applications; in practice, a model trained on labeled CelebA dataset does not work well for test images from a different distribution -- greatly limiting their application to unlabeled images of a much larger quantity. In this paper, we attempt to alleviate this necessity for labeled data in the facial image translation domain. We aim to explore the degree to which you can discover novel attributes from unlabeled faces and perform high-quality translation. To this end, we use prior knowledge about the visual world as guidance to discover novel attributes and transfer them via a novel normalization method. Experiments show that our method trained on unlabeled data produces high-quality translations, preserves identity, and be perceptually realistic as good as, or better than, state-of-the-art methods trained on labeled data.