Semantic Segmentation
3367 papers with code • 81 benchmarks • 237 datasets
Semantic segmentation, or image segmentation, is the task of clustering parts of an image together which belong to the same object class. It is a form of pixel-level prediction because each pixel in an image is classified according to a category. Some example benchmarks for this task are Cityscapes, PASCAL VOC and ADE20K. Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU) and Pixel Accuracy metrics.
( Image credit: CSAILVision )
Benchmarks
These leaderboards are used to track progress in Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Semantic Segmentation models and implementations
COCO
Cityscapes
KITTI
ShapeNet
ScanNet
NYUv2
ADE20K
DAVIS
SYNTHIA
SUN RGB-D
Subtasks
-
Tumor Segmentation
-
Panoptic Segmentation
-
3D Semantic Segmentation
-
Weakly-Supervised Semantic Segmentation
-
Weakly-Supervised Semantic Segmentation
-
Scene Segmentation
-
Real-Time Semantic Segmentation
-
Semi-Supervised Semantic Segmentation
-
3D Part Segmentation
-
Unsupervised Semantic Segmentation
-
One-Shot Segmentation
-
UNET Segmentation
-
Crack Segmentation
-
Polyp Segmentation
-
4D Spatio Temporal Semantic Segmentation
-
Road Segementation
-
Attentive segmentation networks
-
Text-Line Extraction
-
Histopathological Segmentation
-
Aerial Video Semantic Segmentation
-
Amodal Panoptic Segmentation
Latest papers with no code
Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors
Recent diffusion-based generative models combined with vision-language models are capable of creating realistic images from natural language prompts.
FLAIR #1: semantic segmentation and domain adaptation dataset
The French National Institute of Geographical and Forest Information (IGN) has the mission to document and measure land-cover on French territory and provides referential geographical datasets, including high-resolution aerial images and topographic maps.
One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning
It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes.
OCTET: Object-aware Counterfactual Explanations
We conduct a set of experiments on counterfactual explanation benchmarks for driving scenes, and we show that our method can be adapted beyond classification, e. g., to explain semantic segmentation models.
Synthetic Data for Semantic Image Segmentation of Imagery of Unmanned Spacecraft
Images of spacecraft photographed from other spacecraft operating in outer space are difficult to come by, especially at a scale typically required for deep learning tasks.
Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentation
Semi-supervised semantic segmentation focuses on the exploration of a small amount of labeled data and a large amount of unlabeled data, which is more in line with the demands of real-world image understanding applications.
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted.
Rethinking Implicit Neural Representations for Vision Learners
Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks.
ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations.
Label Mask AutoEncoder(L-MAE): A Pure Transformer Method to Augment Semantic Segmentation Datasets
Semantic segmentation models based on the conventional neural network can achieve remarkable performance in such tasks, while the dataset is crucial to the training model process.
