arXiv (Cornell University) · 2018 · 235 citations · 22 references
ComputingComputer ScienceComputer VisionMachine LearningVisual AttentionAttention NetworksDeep LearningFeature-based AttentionScene UnderstandingSemantic SegmentationSpatial AttentionAttentionContextual Feature RepresentationConvolutionEncoder-decoder ArchitecturesFeature PoolingFeature Pyramid NetworksGlobal PoolingSpatial Attention Networks
A Pyramid Attention Network(PAN) is proposed to exploit the impact of global contextual information in semantic segmentation. Different from most existing works, we combine attention mechanism and spatial pyramid to extract precise dense features for pixel labeling instead of complicated dilated convolution and artificially designed decoder networks. Specifically, we introduce a Feature Pyramid Attention module to perform spatial pyramid attention structure on high-level output and combining global pooling to learn a better feature representation, and a Global Attention Upsample module on each decoder layer to provide global context as a guidance of low-level features to select category localization details. The proposed approach achieves state-of-the-art performance on PASCAL VOC 2012 and Cityscapes benchmarks with a new record of mIoU accuracy 84.0% on PASCAL VOC 2012, while training without COCO dataset.
22
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Squeeze-and-Excitation Networks
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi et al. · 2017 · 15.5K citations