Weakly Supervised Instance Segmentation Based on Two-Stage Transfer Learning

Weakly supervised instance segmentation, which could greatly decrease financial and time cost, is one of fundamental computer vision tasks. State-of-the-art methods mainly concentrate on improving the quality of generated pixel level labels, namely masks, using complex traditional segmentation metho...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Yongqing Sun, Shisha Liao, Chenqiang Gao, Chengjuan Xie, Feng Yang, Yue Zhao, Atsushi Sagata
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2020-01-01
Serier:	IEEE Access
Fag:	Weakly supervised instance segmentation transfer learning
Online adgang:	https://ieeexplore.ieee.org/document/8977326/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!