…Each RGB image has a corresponding depth and segmentation map. As many as 700 object categories are labeled. The training and testing sets contain 5285 and 5050 images, respectively.
421 PAPERS • 13 BENCHMARKS
The ADE20K semantic segmentation dataset contains more than 20K scene-centric images exhaustively annotated with pixel-level objects and object parts labels.
991 PAPERS • 25 BENCHMARKS
…In the semantic segmentation task, this dataset is marked in 20 classes of annotated 3D voxelized objects.
1,229 PAPERS • 19 BENCHMARKS
…This dataset can also be used for other learning use-cases, like instance segmentation or depth estimation. Or where household objects or continual learning are of interest. In addition, we also provide a corresponding depth, segmentation, and normal image. In addition to the RGB, depth, segmentation, and normal images, we also provide the calculated features of the RGB images (by ResNet50) as used in our RECALL paper.
1 PAPER • 2 BENCHMARKS