江苏龙网

  1. 首页 > 人文 > >

三好先森|ECCV'20 |OCRNet化解语义分割上下文信息缺失难题( 四 )


更多技术细节可参考如下论文以及开源代码：
论文链接：
代码链接：https://github.com/openseg-group/openseg.pytorch
引用：
[1] The cityscapes dataset for semantic urban scene understanding, CVPR2016
[2] Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing, CVPR2017
[3] Scene parsing through ade20k dataset, CVPR207
[4] Coco-stuff: Thing and stuff classes in context, CVPR2018
[5] Fully convolutional networks for semantic segmentation, CVPR2015
[6] U-net: Convolutional networks for biomedical image segmentation, MICCAI2015
[7] Deep High-Resolution Representation Learning for Visual Recognition, PAMI2020
[8] Object-Contextual Representations for Semantic Segmentation, ECCV2020
[9] SegFix: Model-Agnostic Boundary Refinement for Segmentation, ECCV2020
【三好先森|ECCV'20 |OCRNet化解语义分割上下文信息缺失难题】[10] Parsenet: Looking wider to see better, ICLR2016
[11] Pyramid scene parsing network, CVPR2017
[12] Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, PAMI2017
[13] Rethinking atrous convolution for semantic image segmentation, arXiv: 1706.05587
[14] Panoptic Feature Pyramid Networks, CVPR2019
[15]
[16] Hierarchical Multi-Scale Attention for Semantic Segmentation, arXiv:2005.10821
[17] AinnoSeg: Panoramic Segmentation with High Performance, arXiv:2007.10591


推荐阅读


上一篇：稚久|不会模仿照片色调？送你一键仿色神器 辅助PS调出更美色彩

下一篇：excel|表白，用Excel试试！抖音爆红，一晚点赞破百万！