Standard active learning: active learning without adversarial training
Robust active learning: active learning with adversarial training
1. We conduct an empirical study on 11 acquisition functions, 4 datasets, 6 DNN architectures, and 15105 trained DNNs to check the performance of these functions in active learning.
2. We investigate the characteristics of selected data to explore hints of useful data for robust active learning.
3. We propose the first acquisition function for robust active learning, the density-based robust sampling with entropy (DRE), and demonstrate the efficiency of DRE.
4. We apply DRE to test selection for model retraining.