# Face Parsing via Recurrent Propagation

arXiv: https://arxiv.org/abs/1708.01936 · HTML: https://mlsanity.com/paper/1708.01936/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2017.

## Built on by (most cited first, 14 of 14)

- [Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing](https://mlsanity.com/paper/2203.14448/) (2022)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [SegFace: Face Segmentation of Long-Tail Classes](https://mlsanity.com/paper/2412.08647/) (2024)
- [AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2101.07034/) (2021)
- [Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GAN](https://mlsanity.com/paper/2212.09098/) (2022)
- [Parameter Efficient Local Implicit Image Function Network for Face Segmentation](https://mlsanity.com/paper/2303.15122/) (2023)
- [Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal](https://mlsanity.com/paper/2104.09457/) (2021)
- [DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing](https://mlsanity.com/paper/2508.01250/) (2025)
- [Transparent Model of Unabridged Data (TMUD)](https://mlsanity.com/paper/2106.07558/) (2021)
- [Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination](https://mlsanity.com/paper/2203.16669/) (2022)
- [CADA-GAN: Context-Aware GAN with Data Augmentation](https://mlsanity.com/paper/2301.08849/) (2023)
- [Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsing](https://mlsanity.com/paper/2308.15323/) (2023)
- [S3POT: Contrast-Driven Face Occlusion Segmentation via Self-Supervised Prompt Learning](https://mlsanity.com/paper/2602.00635/) (2026)

## Abstract (arXiv)

Face parsing is an important problem in computer vision that finds numerous applications including recognition and editing. Recently, deep convolutional neural networks (CNNs) have been applied to image parsing and segmentation with the state-of-the-art performance. In this paper, we propose a face parsing algorithm that combines hierarchical representations learned by a CNN, and accurate label propagations achieved by a spatially variant recurrent neural network (RNN). The RNN-based propagation approach enables efficient inference over a global space with the guidance of semantic edges generated by a local convolutional model. Since the convolutional architecture can be shallow and the spatial RNN can have few parameters, the framework is much faster and more light-weighted than the state-of-the-art CNNs for the same task. We apply the proposed model to coarse-grained and fine-grained face parsing. For fine-grained face parsing, we develop a two-stage approach by first identifying the main regions and then segmenting the detail components, which achieves better performance in terms of accuracy and efficiency. With a single GPU, the proposed algorithm parses face images accurately at 300 frames per second, which facilitates real-time applications.