DeeperLab: Single-Shot Image Parser
arXiv: Computer Vision and Pattern Recognition, 2019.
We present a single-shot, bottom-up approach for whole image parsing. Whole image parsing, also known as Panoptic Segmentation, generalizes the tasks of semantic segmentation for u0027stuffu0027 classes and instance segmentation for u0027thingu0027 classes, assigning both semantic and instance labels to every pixel in an image. Recent app...More
PPT (Upload PPT)