TY  - STD
AU  - Umut Guclu
AU  - Yagmur Gucluturk
AU  - Meysam Madadi
AU  - Sergio Escalera
AU  - Xavier Baro
AU  - Jordi Gonzalez
AU  - Rob van Lier
AU  - Marcel A. J. van Gerven
PY  - 2017//
TI  - End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/GGM2017.pdf
N1  - HuPBA; ISE; 600.098; 600.119
ID  - Umut Guclu2017
ER  -