# Towards Learning Structure via Consensus for Face Segmentation and Parsing

arXiv: https://arxiv.org/abs/1911.00957 · HTML: https://mlsanity.com/paper/1911.00957/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2019.

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

- [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)
- [Automatic Animation of Hair Blowing in Still Portrait Photos](https://mlsanity.com/paper/2309.14207/) (2023)
- [Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors](https://mlsanity.com/paper/2408.12387/) (2024)
- [Segmentation-Reconstruction-Guided Facial Image De-occlusion](https://mlsanity.com/paper/2112.08022/) (2021)
- [FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction](https://mlsanity.com/paper/2201.08425/) (2022)
- [Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsing](https://mlsanity.com/paper/2308.15323/) (2023)
- [3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes](https://mlsanity.com/paper/2412.19849/) (2024)

## Abstract (arXiv)

Face segmentation is the task of densely labeling pixels on the face according to their semantics. While current methods place an emphasis on developing sophisticated architectures, use conditional random fields for smoothness, or rather employ adversarial training, we follow an alternative path towards robust face segmentation and parsing. Occlusions, along with other parts of the face, have a proper structure that needs to be propagated in the model during training. Unlike state-of-the-art methods that treat face segmentation as an independent pixel prediction problem, we argue instead that it should hold highly correlated outputs within the same object pixels. We thereby offer a novel learning mechanism to enforce structure in the prediction via consensus, guided by a robust loss function that forces pixel objects to be consistent with each other. Our face parser is trained by transferring knowledge from another model, yet it encourages spatial consistency while fitting the labels. Different than current practice, our method enjoys pixel-wise predictions, yet paves the way for fewer artifacts, less sparse masks, and spatially coherent outputs.