Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Cha, Sinhae"'
Publikováno v:
Engineering Applications of Artificial Intelligence, 2024
Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localizatio
Externí odkaz:
http://arxiv.org/abs/2404.09475
Publikováno v:
IEEE International Conference on Visual Communications and Image Processing, 2023
This work addresses the task of weakly-supervised object localization. The goal is to learn object localization using only image-level class labels, which are much easier to obtain compared to bounding box annotations. This task is important because
Externí odkaz:
http://arxiv.org/abs/2312.09584