Extracting Structured Supervision From Captions for Weakly Supervised Semantic Segmentation

Extracting Structured Supervision From Captions for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) methods have received significant attention in recent years, since they can dramatically reduce the annotation costs of fully supervised alternatives. While most previous studies focused on leveraging classification labels, we explore instead the use of...

Full description

Bibliographic Details
Main Authors: Daniel R. Vilar, Claudio A. Perez
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Image captions
semantic segmentation
weakly supervised
Online Access:https://ieeexplore.ieee.org/document/9416644/

Internet

https://ieeexplore.ieee.org/document/9416644/

Similar Items