Mask-guided sample selection for Semi-Supervised Instance Segmentation
MULTIMEDIA TOOLS AND APPLICATIONS, pp. 25551.0-25569.0, 2020.
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
PPT (Upload PPT)