RoI Tanh-polar transformer network for face parsing in the wild

作者：

Highlights：

• We transform the whole image to Tanh-polar space to preserve context and to make the convolutions rotational- equivariant.

• We use Hybrid Residual Representation Learning Blocks to extract features in both Tanh-polar and Tanh-Cartesian space.

• We present iBugMask dataset, a novel in-the-wild face parsing bench-mark that consists of more than 22 thousand images.

• We conduct extensive experiments and show that the overall framework, RTNet, improves the state-of-the-art on all benchmarks.

摘要

•We transform the whole image to Tanh-polar space to preserve context and to make the convolutions rotational- equivariant.•We use Hybrid Residual Representation Learning Blocks to extract features in both Tanh-polar and Tanh-Cartesian space.•We present iBugMask dataset, a novel in-the-wild face parsing bench-mark that consists of more than 22 thousand images.•We conduct extensive experiments and show that the overall framework, RTNet, improves the state-of-the-art on all benchmarks.

论文关键词：Face parsing,In-the-wild dataset,Head pose augmentation,Tanh-polar representation

论文评审过程：Received 26 April 2021, Accepted 27 April 2021, Available online 6 May 2021, Version of Record 25 May 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104190