Balancing Bias and Variance for Active Weakly Supervised Learning

• Published in: arXiv.org
• Main Authors: Sapkota, Hitesh, Yu, Qi
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 12.06.2022
• Subjects: Annotations; Bias; Microbalances; Optimization; Robustness; Sampling; Supervised learning; Variance

As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many important applications, remains largely unsatisfactory. We propose to conduct novel act...