In this work, we ask if we may leverage semi-supervised learning in unlabeled video sequences and extra images to improve the performance on urban scene segmentation, simultaneously tackling semantic, instance, and panoptic segmentation. This limitation is particularly notable for image segmentation tasks, where the expense of human annotation is especially large, yet large amounts of unlabeled data may exist. In turn, the efficacy of supervised learning may be limited by the size of the human annotated dataset. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. Supervised learning in large discriminative models is a mainstay for modern computer vision.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
May 2023
Categories |