-
MIT Scene Parsing Dataset
The MIT scene parsing dataset used for training the FCN network. -
Pyramid scene parsing network
Pyramid scene parsing network for semantic segmentation. -
Indoor Segmentation and Support Inference from RGB-D Images
Indoor segmentation and support inference from RGB-D images. -
Visual Genome
The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships. -
Cityscapes
The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...