Self-Correction for Human Parsing

22 Oct 2019 Peike Li Yunqiu Xu Yunchao Wei Yi Yang

Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g. human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearance usually are confusing, leading to unexpected noises in ground truth masks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Human Part Segmentation CIHP ResNet101 Mean IoU 59.36 # 2
Semantic Segmentation LIP val SCHP (ResNet-101) mIoU 59.36% # 1
Human Part Segmentation PASCAL-Part SCHP mIoU 71.46 # 2

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks