Search Results for author:
Found 1 papers, 1 papers with code
Complete Instances Mining for Weakly Supervised Instance Segmentation
To address this problem, we propose a novel approach for WSIS that focuses on the online refinement of complete instances through the use of MaskIoU heads to predict the integrity scores of proposals and a Complete Instances Mining (CIM) strategy to explicitly model the redundant segmentation problem and generate refined pseudo labels.
Ranked #1 on
Image-level Supervised Instance Segmentation
on COCO 2017 val
(using extra training data)
Cannot find the paper you are looking for? You can
Submit a new open access paper.
