Dual Attention Network for Scene Segmentation

CVPR 2019 Jun FuJing LiuHaijie TianYong LiYongjun BaoZhiwei FangHanqing Lu

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

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Semantic Segmentation Cityscapes test DANet (ResNet-101) Mean IoU (class) 81.5% # 17
Semantic Segmentation COCO-Stuff test DANet (ResNet-101) mIoU 39.7% # 2
Semantic Segmentation PASCAL Context DANet (ResNet-101) mIoU 52.6 # 8
Semantic Segmentation PASCAL VOC 2012 test DANet (ResNet-101) Mean IoU 82.6% # 17