Improving Cost Efficiency of Active Learning on Noisy Datasets
The author proposes a shifted normal distribution sampling function to enhance cost efficiency in active learning, particularly in cases of imbalanced labeling costs for positive and negative instances.
Bridging Diversity and Uncertainty in Active Learning with Self-Supervised Pre-Training at ICLR 2024 Workshop
The author introduces the TCM heuristic to combine diversity-based and uncertainty-based sampling strategies in active learning, leveraging self-supervised pre-trained models for improved performance across various data levels.
Active Learning Method SUPClust for Model Optimization
The author introduces the novel active learning method SUPClust, focusing on identifying points at decision boundaries to enhance model performance through informative data labeling.
Efficient Active Learning via Proxy in Pre-trained Models: Addressing Performance Drop
Pre-trained models combined with active learning strategies can reduce annotation costs, but the performance drop in proxy-based active learning needs to be addressed.
Enhancing Students' Learning Process Through Self-Generated Tests: A Study on Active Learning Methodologies in Higher Education
Encouraging students to actively participate in the learning process through self-generated tests improves academic performance.
Self-Supervised Pre-Training in Active Learning for Low Resource Settings
다양성과 불확실성을 결합한 활성 학습의 효과적인 전략 소개
© 2024 by Linnk AI