Weight Decay Scheduling and Knowledge Distillation for Active Learning
Authors:
- 13 November 2020
- book chapter
- Published by Springer Nature
- p. 431-447
Abstract
No abstract availableKeywords
This publication has 23 references indexed in Scilit:
- Randaugment: Practical automated data augmentation with a reduced search space2020
- A Comprehensive Overhaul of Feature Distillation2019
- The Power of Ensembles for Active Learning in Image Classification2018
- Densely Connected Convolutional Networks2017
- Deep Networks with Stochastic Depth2016
- Deep Residual Learning for Image Recognition2016
- Selecting Influential Examples: Active Learning with Expected Model Output Changes2014
- A Convex Optimization Framework for Active Learning2013
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Heterogeneous Uncertainty Sampling for Supervised Learning1994