Edge-aware Graph Representation Learning and Reasoning for Face Parsing

ECCV 2020  ·  Gusi Te, Yinglu Liu, Wei Hu, Hailin Shi, Tao Mei ·

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.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Parsing CelebAMask-HQ EAGR Mean F1 85.1 # 4
Face Parsing LaPa EAGR Mean F1 91.1 # 5

Methods


No methods listed for this paper. Add relevant methods here