works on
calibration 1loss functions 1multi-instance learning 1partial-label learning 1weak supervision 1

From the 1 of 2 linked papers with an AI index.

collaborators

2 papers

cs.LG2026

Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning

Wei Tang, Yin-Fang Yang, Weijia Zhang +1

The paper introduces a calibratable disambiguation loss (CDL) that improves both classification accuracy and confidence calibration for multi-instance partial-label learning by inc…

cs.LG2025

Multi-Instance Partial-Label Learning with Margin Adjustment

Wei Tang, Yin-Fang Yang, Zhaofei Wang +2

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label s…