Few-shot semantic segmentation with self-supervision from pseudo-classes

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron: Li, Y, Data, GWP, Fu, Y, Hu, Y, Prisacariu, VA
Fformat: Conference item
Iaith:English
Cyhoeddwyd: British Machine Vision Association 2021

Eitemau Tebyg