BriefGPT.xyz
Dec, 2023
DIRECT: 不平衡和标签噪音下的深度主动学习
DIRECT: Deep Active Learning under Imbalance and Label Noise
HTML
PDF
Shyam Nuggehalli, Jifan Zhang, Lalit Jain, Robert Nowak
TL;DR
通过一种新颖的算法 DIRECT，该论文提出了解决机器学习中不平衡问题的有效技术，通过收集更平衡和信息丰富的标记示例来进行注释，相较于现有算法，该算法节省了超过15%的注释预算。
Abstract
class imbalance
is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and
minority classes
. With an abundance of wild unlabeled data,
→