PASCAL Context

ImagesUnknownIntroduced 2014-01-01

The PASCAL Context dataset is an extension of the PASCAL VOC 2010 detection challenge, and it contains pixel-wise labels for all training images. It contains more than 400 classes (including the original 20 classes plus backgrounds from PASCAL VOC segmentation), divided into three categories (objects, stuff, and hybrids). Many of the object categories of this dataset are too sparse and; therefore, a subset of 59 frequent classes are usually selected for use.

Source: Image Segmentation Using Deep Learning:A Survey Image Source: https://cs.stanford.edu/~roozbeh/pascal-context/

Benchmarks

10-shot image generation/mIoU 10-shot image generation/Mean Accuracy 10-shot image generation/Pixel Accuracy Boundary Detection/odsF Human Parsing/mIoU Saliency Detection/max_F1 Semantic Segmentation/mIoU Semantic Segmentation/Mean Accuracy Semantic Segmentation/Pixel Accuracy Surface Normals Estimation/Mean Angle Error Zero-Shot Learning/k=10 mIOU

Related Benchmarks

PASCAL Context 12.5% labeled/10-shot image generation/Validation mIoU PASCAL Context 12.5% labeled/Semantic Segmentation/Validation mIoU PASCAL Context 25% labeled/10-shot image generation/Validation mIoU PASCAL Context 25% labeled/Semantic Segmentation/Validation mIoU PASCAL Context val/10-shot image generation/mIoU PASCAL Context val/Semantic Segmentation/mIoU PASCAL Context-459/Open Vocabulary Semantic Segmentation/mIoU PASCAL Context-59/10-shot image generation/mIoU PASCAL Context-59/Open Vocabulary Semantic Segmentation/mIoU PASCAL Context-59/Semantic Segmentation/mIoU PASCAL Context-59/Unsupervised Semantic Segmentation/mIoU PASCAL Context-60/10-shot image generation/mIoU PASCAL Context-60/Semantic Segmentation/mIoU PASCAL Context-60/Unsupervised Semantic Segmentation/mIoU