Improving greedy core-set configurations for active learning with uncertainty-scaled distances
Not on the map. Why?
Abstract (arXiv)
We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification, especially in larger acquisition sizes. We show the necessity of our modifications and explain how the improvement is due to a probabilistic quadratic speed-up in the convergence of core-set loss, under assumptions about the relationship of model uncertainty and misclassification.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 14 references that are in the map. First posted on arXiv 9 Feb 2022.
Builds on
7 of 14 references.
References · 7
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
- 2019Variational Adversarial Active Learningcited by 284
- 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
- 2017Deep Active Learning for Named Entity Recognitioncited by 108
Built on by
Not cited yet.