Dual Attention Network for Scene Segmentation

In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Segmentation Cityscapes test DANet (ResNet-101) Mean IoU (class) 81.5% # 31
Semantic Segmentation COCO-Stuff test DANet (ResNet-101) mIoU 39.7% # 7
Semantic Segmentation PASCAL Context DANet (ResNet-101) mIoU 52.6 # 26
Semantic Segmentation PASCAL VOC 2012 test DANet (ResNet-101) Mean IoU 82.6% # 30

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
FCN
Semantic Segmentation Models
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