Pyramid Attention Network for Semantic Segmentation
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes
LSegDiff: A Latent Diffusion Model for Medical Image Segmentation
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images
Crosslink-Net: Double-Branch Encoder Network via Fusing Vertical and Horizontal Convolutions for Medical Image Segmentation
FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene
토론
이 논문과 연결된 포럼 글이 아직 없습니다.