Can Calibration Improve Sample Prioritization?
Not on the map. Why?
Abstract (arXiv)
Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training? In this paper, we show that it can when used to prioritize some examples for performing subset selection. We study the effect of popular calibration techniques in selecting better subsets of samples during training (also called sample prioritization) and observe that calibration can improve the quality of subsets, reduce the number of examples per epoch (by at least 70%), and can thereby speed up the overall training process. We further study the effect of using calibrated pre-trained models coupled with calibration during training to guide sample prioritization, which again seems to improve the quality of samples selected.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 15 references that are in the map. First posted on arXiv 12 Oct 2022.
Builds on
10 of 15 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2019When Does Label Smoothing Help?cited by 988
- 2019Measuring Calibration in Deep Learningcited by 446
- 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
- 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
- 2020Calibrating Deep Neural Networks using Focal Losscited by 357
- 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
Built on by
Not cited yet.