Mask-guided sample selection for Semi-Supervised Instance Segmentation

Miriam Bellver
Miriam Bellver
Jordi Torres
Jordi Torres
Xavier Giro-i-Nieto
Xavier Giro-i-Nieto

MULTIMEDIA TOOLS AND APPLICATIONS, pp. 25551.0-25569.0, 2020.

Cited by: 0|Views10
EI

Abstract:

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. Weakly-supervised pipelines are the most common solution to address this constraint because they are trained with lower forms of supervision, such as bounding boxes or scribbles. Semi-supervised methods are anoth...More

Code:

Data:

Your rating :
0

 

Tags
Comments