# Edge-aware Graph Representation Learning and Reasoning for Face Parsing

arXiv: https://arxiv.org/abs/2007.11240 · HTML: https://mlsanity.com/paper/2007.11240/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2020.

## Built on by (most cited first, 26 of 26)

- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing](https://mlsanity.com/paper/2203.14448/) (2022)
- [Sparse to Dense Motion Transfer for Face Image Animation](https://mlsanity.com/paper/2109.00471/) (2021)
- [Fully Transformer Networks for Semantic Image Segmentation](https://mlsanity.com/paper/2106.04108/) (2021)
- [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)
- [Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection](https://mlsanity.com/paper/2408.15020/) (2024)
- [AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2101.07034/) (2021)
- [Automatic Animation of Hair Blowing in Still Portrait Photos](https://mlsanity.com/paper/2309.14207/) (2023)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Face-MLLM: A Large Face Perception Model](https://mlsanity.com/paper/2410.20717/) (2024)
- [Toward High Quality Facial Representation Learning](https://mlsanity.com/paper/2309.03575/) (2023)
- [Parameter Efficient Local Implicit Image Function Network for Face Segmentation](https://mlsanity.com/paper/2303.15122/) (2023)
- [CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation](https://mlsanity.com/paper/2508.06625/) (2025)
- [FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO](https://mlsanity.com/paper/2503.09158/) (2025)
- [Graph-based Pyramid Global Context Reasoning with a Saliency-aware Projection for COVID-19 Lung Infections Segmentation](https://mlsanity.com/paper/2103.04235/) (2021)
- [SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models](https://mlsanity.com/paper/2406.07840/) (2024)
- [PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training](https://mlsanity.com/paper/2508.09691/) (2025)
- [Shuffle Transformer with Feature Alignment for Video Face Parsing](https://mlsanity.com/paper/2106.08650/) (2021)
- [Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images](https://mlsanity.com/paper/2207.01871/) (2022)
- [3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes](https://mlsanity.com/paper/2412.19849/) (2024)

## Abstract (arXiv)

Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently. Previous methods have shown their efficiency in face parsing, which however overlook the correlation among different face regions. The correlation is a critical clue about the facial appearance, pose, expression etc., and should be taken into account for face parsing. To this end, we propose to model and reason the region-wise relations by learning graph representations, and leverage the edge information between regions for optimized abstraction. Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex. Our model learns and reasons over relations between the regions by propagating information across vertices on the graph. Furthermore, we incorporate the edge information to aggregate the pixel-wise features onto vertices, which emphasizes on the features around edges for fine segmentation along edges. The finally learned graph representation is projected back to pixel grids for parsing. Experiments demonstrate that our model outperforms state-of-the-art methods on the widely used Helen dataset, and also exhibits the superior performance on the large-scale CelebAMask-HQ and LaPa dataset. The code is available at https://github.com/tegusi/EAGRNet.