Quality-Aware Network for Face Parsing
arXiv:2106.07368
Abstract
This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. Face parsing has recently attracted increasing interest due to its numerous application potentials. Generally speaking, it has a lot in common with human parsing, such as task setting, data characteristics, number of categories and so on. Therefore, this work applies state-of-the-art human parsing method to face parsing task to explore the similarities and differences between them. Our submission achieves 86.84% score and wins the 2nd place in the challenge.
arXiv comment2nd place in Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- FCOS: Fully Convolutional One-Stage Object Detection
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Pyramid Scene Parsing Network
- MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
- MegDet: A Large Mini-Batch Object Detector
- Instance-level Human Parsing via Part Grouping Network
- Hierarchical Human Parsing with Typed Part-Relation Reasoning
- Face Parsing with RoI Tanh-Warping
- Parsing R-CNN for Instance-Level Human Analysis
- Quality-Aware Network for Human Parsing