2D Semantic Segmentation
38 papers with code • 9 benchmarks • 57 datasets
Benchmarks
These leaderboards are used to track progress in 2D Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
Cityscapes
CamVid
KITTI-360
xBD
KITTI MOTS
SpaceNet 7
WaterScenes
DeepSport Dataset
Subtasks
Most implemented papers
xBD: A Dataset for Assessing Building Damage from Satellite Imagery
DIUx-xView/xview2-baseline
•
•
xBD is the largest building damage assessment dataset to date, containing 850, 736 building annotations across 45, 362 km\textsuperscript{2} of imagery.
Realtime Global Attention Network for Semantic Segmentation
In this paper, we proposed an end-to-end realtime global attention neural network (RGANet) for the challenging task of semantic segmentation.
Normalization in Training U-Net for 2D Biomedical Semantic Segmentation
XiaoYunZhou27/UNet-with-BN-GN-IN-LN
•
•
In this paper, four normalization methods - BN, IN, LN and GN are compared in details, specifically for 2D biomedical semantic segmentation.
See and Think: Disentangling Semantic Scene Completion
ShiceLiu/SATNet
•
•
NeurIPS 2018
Semantic scene completion predicts volumetric occupancy and object category of a 3D scene, which helps intelligent agents to understand and interact with the surroundings.
3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many of these real-world applications.
Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion
Automatic change detection and disaster damage assessment are currently procedures requiring a huge amount of labor and manual work by satellite imagery analysts.
SofGAN: A Portrait Image Generator with Dynamic Styling
apchenstu/sofgan
•
•
To address this issue, we propose a SofGAN image generator to decouple the latent space of portraits into two subspaces: a geometry space and a texture space.
Virtual Multi-view Fusion for 3D Semantic Segmentation
YanjieZe/Virtual-Multi-View-Fusion
•
•
ECCV 2020
Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels.
Bidirectional Projection Network for Cross Dimension Scene Understanding
wbhu/BPNet
•
•
CVPR 2021
Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.
Self-Improving Semantic Perception for Indoor Localisation
ethz-asl/background_foreground_segmentation
•
•
We find memory replay an effective measure to reduce forgetting and show how the robotic system can improve even when switching between different environments.
