## Frontmatter | | | | --- | --- | | Authors | [[Umut Güçlü]], [[Yağmur Güçlütürk]], [[Meysam Madadi]], [[Sergio Escalera]], [[Xavier Baró]], [[Jordi González]], [[Rob van Lier]], [[Marcel van Gerven]] | | Date | 2017/03 | | Source | [[arXiv]] | | URL | https://doi.org/10.48550/arXiv.1703.03305 | | Citation | Güçlü, U., Güçlütürk, Y., Madadi, M., Escalera, S., Baró, X., González, J., van Lier, R., & van Gerven, M. (2017). [[End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks]]. _arXiv_. [[URL](https://doi.org/10.48550/arXiv.1703.03305)]. #Preprint | ## Abstract 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 ![[End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks.pdf]]