%0 Generic
%T End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks
%A Umut Guclu
%A Yagmur Gucluturk
%A Meysam Madadi
%A Sergio Escalera
%A Xavier Baro
%A Jordi Gonzalez
%A Rob van Lier
%A Marcel A. J. van Gerven
%D 2017
%F Umut Guclu2017
%O HuPBA; ISE; 600.098; 600.119
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2932), last updated on Fri, 19 Feb 2021 09:38:58 +0100
%X arXiv:1703.03305 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 pairwisepotentials, 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.
%9 miscellaneous
%U http://refbase.cvc.uab.es/files/GGM2017.pdf