# Toward High Quality Facial Representation Learning arXiv: https://arxiv.org/abs/2309.03575 ยท HTML: https://mlsanity.com/paper/2309.03575/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 35 references that are in the map. - First posted on arXiv 7 Sep 2023. ## Builds on (most cited first, 26 of 26) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019) - [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021) - [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021) - [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018) - [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020) - [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021) - [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021) - [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021) - [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018) - [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021) - [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019) - [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021) - [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019) - [PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers](https://mlsanity.com/paper/2111.12710/) (2021) - [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021) - [MST: Masked Self-Supervised Transformer for Visual Representation](https://mlsanity.com/paper/2106.05656/) (2021) - [EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm](https://mlsanity.com/paper/2206.09325/) (2022) - [Edge-aware Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2007.11240/) (2020) - [Pre-training strategies and datasets for facial representation learning](https://mlsanity.com/paper/2103.16554/) (2021) - [Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing](https://mlsanity.com/paper/2203.14448/) (2022) - [Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model](https://mlsanity.com/paper/2105.15089/) (2021) - [AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2101.07034/) (2021) - [Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion](https://mlsanity.com/paper/2004.06558/) (2020) ## Built on by (most cited first, 10 of 10) - [FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning](https://mlsanity.com/paper/2412.12032/) (2024) - [Self-Supervised Facial Representation Learning with Facial Region Awareness](https://mlsanity.com/paper/2403.02138/) (2024) - [Representation Learning and Identity Adversarial Training for Facial Behavior Understanding](https://mlsanity.com/paper/2407.11243/) (2024) - [UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training](https://mlsanity.com/paper/2502.02307/) (2025) - [SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data](https://mlsanity.com/paper/2410.09865/) (2024) - [D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition](https://mlsanity.com/paper/2406.16473/) (2024) - [PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training](https://mlsanity.com/paper/2508.09691/) (2025) - [Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions](https://mlsanity.com/paper/2601.00156/) (2026) - [Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning](https://mlsanity.com/paper/2508.19730/) (2025) - [Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets](https://mlsanity.com/paper/2605.29720/) (2026) ## Abstract (arXiv) Face analysis tasks have a wide range of applications, but the universal facial representation has only been explored in a few works. In this paper, we explore high-performance pre-training methods to boost the face analysis tasks such as face alignment and face parsing. We propose a self-supervised pre-training framework, called it Mask Contrastive Face (MCF), with mask image modeling and a contrastive strategy specially adjusted for face domain tasks. To improve the facial representation quality, we use feature map of a pre-trained visual backbone as a supervision item and use a partially pre-trained decoder for mask image modeling. To handle the face identity during the pre-training stage, we further use random masks to build contrastive learning pairs. We conduct the pre-training on the LAION-FACE-cropped dataset, a variants of LAION-FACE 20M, which contains more than 20 million face images from Internet websites. For efficiency pre-training, we explore our framework pre-training performance on a small part of LAION-FACE-cropped and verify the superiority with different pre-training settings. Our model pre-trained with the full pre-training dataset outperforms the state-of-the-art methods on multiple downstream tasks. Our model achieves 0.932 NMEdiag for AFLW-19 face alignment and 93.96 F1 score for LaPa face parsing. Code is available at https://github.com/nomewang/MCF.