Obviously Awesome

Weakly- and Semi-Supervised Learning
Fully Convolutional Networks for Semantic Segmentation (PAMI, 2016)
U-Net: Convolutional Networks for Biomedical Image Segmentation (MICCAI, 2015)
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation (2017)
Multi-Scale Context Aggregation by Dilated Convolutions (ICLR, 2016)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (TPAMI, 2017)
Rethinking Atrous Convolution for Semantic Image Segmentation (2017)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (ECCV, 2018)
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation (2019)
Improving Semantic Segmentation via Video Propagation and Label Relaxation (CVPR, 2019)
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation (2019)