Self-adaptive Training is a training algorithm that dynamically corrects problematic training labels by model predictions to improve generalization of deep learning for potentially corrupted training data. Accumulated predictions are used to augment the training dynamics. The use of an exponential-moving-average scheme alleviates the instability issue of model predictions, smooths out the training target during the training process and enables the algorithm to completely change the training labels if necessary.
Source: Self-Adaptive Training: beyond Empirical Risk MinimizationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Autonomous Driving | 1 | 20.00% |
Reinforcement Learning (RL) | 1 | 20.00% |
Self-Learning | 1 | 20.00% |
Self-Supervised Learning | 1 | 20.00% |
General Classification | 1 | 20.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |