← Research

End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks

Umut G\"u\c{c}l\"u, Ya\u{g}mur G\"u\c{c}l\"ut\"urk, Meysam Madadi, Sergio Escalera, Xavier Bar\'o, Jordi Gonz\'alez, Rob van Lier, Marcel A. J. van Gerven

Recent years have seen a sharp increase in the number of related yet distinct advances in semantic segmentation. Here, we tackle this problem by leveraging the respective strengths of these advances. That is, we formulate a conditional random field over a four-connected graph as end-to-end trainable convolutional and recurrent networks, and estimate them via an adversarial process. Importantly, our model learns not only unary potentials but also pairwise potentials, while aggregating multi-scale contexts and controlling higher-order inconsistencies. We evaluate our model on two standard benchmark datasets for semantic face segmentation, achieving state-of-the-art results on both of them.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace