Deep learning methods with less supervision

Deep learning methods with less supervision

To tackle the immense burden of acquiring accurate, pixel-level annotations for semantic segmentation tasks, we propose a weakly-supervised deep learning framework. We incorporate state-of-the-art foundational models to propagate pseudo-labels. Then, explore the viability of training a fully convolu...

Mô tả đầy đủ

Chi tiết về thư mục
Tác giả chính: Chai, Youxiang
Tác giả khác: Lin Guosheng
Định dạng: Final Year Project (FYP)
Ngôn ngữ:English
Được phát hành: Nanyang Technological University 2023
Những chủ đề:
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Truy cập trực tuyến:https://hdl.handle.net/10356/172909

Internet

https://hdl.handle.net/10356/172909

Những quyển sách tương tự