LSUN 2015 - Large-scale Scene Understanding Challenge Workshop

PASCAL VOC and ImageNet ILSVRC challenges have enabled significant progress for object recognition in the past decade. We propose to borrow this mechanism to speed up the progress for scene understanding as well. Complementary to the object-centric ImageNet ILSVRC Challenge hosted at ICCV/ECCV every year, we propose to host a scene-centric challenge at CVPR every year. Our challenge will focus on three major tasks in scene understanding, including scene classification, saliency prediction, and room layout estimation. Inspired by recent success using big data, such as deep learning, we will focus on providing benchmarks that are at least 10 times bigger than the existing ones, to support training these data-hungry algorithms. To ensure fairness, we explicitly exclude every image from all existing datasets (such as SUN, Places and ImageNet). By providing a set of large-scale benchmarks in an annual challenge format, we expect significant progress to be made for scene understanding in the coming years.