- A Relation-Augmented Fully Convolutional Network for Semantic Segmentationin Aerial Scenes
 - 3D Graph Neural Networks for RGBD Semantic Segmentation
 - Decoders Matter for Semantic Segmentation:Data-Dependent Decoding Enables Flexible Feature Aggregation
 - FickleNet: Weakly and Semi-supervised Semantic Image Segmentationusing Stochastic Inference
 - Understand Convolution for Semantic Segmentation
 - DenseASPP for Semantic Segmentation in Street Scenes
 - Dilated Residual Networks
 - Dual Attention Network for Scene Segmentation
 - Context Encoding for Semantic Segmentation
 - Adaptive Affinity Fields for Semantic Segmentation
 - Superpixel Sampling Networks
 - FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
 - Large Kernel Matters —— Improve Semantic Segmentation by Global Convolutional Network
 - LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
 - Learning a Discriminative Feature Network for Semantic Segmentation
 - StructToken: Rethinking Semantic Segmentation with Structural Prior
 - Gated Feedback Refinement Network for Dense Image Labeling
 - Semi-convolutional Operators forInstance Segmentation
 - Dynamic Filtering with Large Sampling Field for ConvNets
 - Dynamic Filter Networks
 - Dynamic Filters for Semantic Segmentation
 - Depth与Convolution
 - Segmenting Transparent Objects in the Wild
 - Conditional Convolutions for Instance Segmentation
 - SegFix: Model-Agnostic Boundary Refinement for Segmentation
 - Dual Super-Resolution Learning for Semantic Segmentation
 - 使用bi-directional propagation来获取全局上下文
 - Towards Enhancing Fine-grained Details for Image Matting
 - U-Net Transformer: Self and Cross Attention for Medical Image Segmentation
 - Dense Prediction with Attentive Feature Aggregation
 
