A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials

Måns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng 0001, Philip H. S. Torr. A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials. In Marcello Pelillo, Edwin R. Hancock, editors, Energy Minimization Methods in Computer Vision and Pattern Recognition - 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, Revised Selected Papers. Volume 10746 of Lecture Notes in Computer Science, pages 564-579, Springer, 2017. [doi]

Abstract

Abstract is missing.