Learning Structure via Consensus for Face Segmentation and Parsing

by   Iacopo Masi, et al.

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.


page 1

page 3

page 6

page 7

page 8

page 10

page 11


3D Face Parsing via Surface Parameterization and 2D Semantic Segmentation Network

Face parsing assigns pixel-wise semantic labels as the face representati...

Pixel Consensus Voting for Panoptic Segmentation

The core of our approach, Pixel Consensus Voting, is a framework for ins...

Region Mutual Information Loss for Semantic Segmentation

Semantic segmentation is a fundamental problem in computer vision. It is...

Parameter Efficient Local Implicit Image Function Network for Face Segmentation

Face parsing is defined as the per-pixel labeling of images containing h...

Towards Open-World Segmentation of Parts

Segmenting object parts such as cup handles and animal bodies is importa...

Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss

We devise a cascade GAN approach to generate talking face video, which i...

Please sign up or login with your details

Forgot password? Click here to reset