computer-vision-15
Semantic Segmentation
3260 papers • 126 benchmarks • 313 datasets
Semantic Segmentation is a computer vision task in which the goal is to categorize each pixel in an image into a class or object. The goal is to produce a dense pixel-wise segmentation map of an image, where each pixel is assigned to a specific class or object. 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 )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in semantic-segmentation-15
Trend
Dataset
Best Model
Actions
ADE20K
ADE20K
NYU Depth v2
NYU Depth v2
Cityscapes test
Cityscapes test
Libraries
iUse these libraries to find semantic-segmentation-15 models and implementations
53 papers 8,290
