.png){kind=icon}
返回
Overcoming Overconfidence for Active Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3449915.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent advances in artificial intelligence undeniably depend on vast amounts of high-quality data. However, a persistent global challenge is the restricted budgets allocated for data labeling. To address this, active learning emerges as a prominent and efficient strategy. It involves iterative selections of valuable data for labeling through a model and updating the model based on these selections. Nonetheless, the limited data available in each iteration renders the model susceptible to bias, resulting in potentially overconfident predictions. To mitigate this issue, we propose the Overcoming Overconfidence for Active Learning (OO4AL) framework. This framework comprises two parts: Cross-Mix-and-Mix, an augmentation strategy aimed at broadening the training distribution to calibrate the model, and Ranked Margin Sampling, a selection strategy that prevents the selection of overconfidence-inducing data by evaluating predictions. Through comprehensive experiments and analyses, we demonstrate that our framework facilitates efficient data selection by reducing overconfidence, though it can be readily implemented.
Keyword:
Data models
Uncertainty
Training data
Predictive models
Labeling
Calibration
Image classification
Data integrity
Active learning
model calibration
image classification
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Mechanisms of Disease: local renin–angiotensin–aldosterone systems and the pathogenesis and treatment of cardiovascular disease疾病机制: 局部肾素-血管紧张素-醛固酮系统与心血管疾病的发病机制和治疗
PREAI
分享收藏Elimination of O2 plasma damage of low-k methyl silsesquioxane film by As implantation通过As注入消除低k甲基倍半硅氧烷膜的O2等离子体损伤
PREAI
分享收藏
查看更多内容