Class-incremental continual learning method based on classification layer unification and improved ewc
By adjusting the weights and mean bias vector in the EWC method and assigning greater weights to samples with high confidence, the catastrophic forgetting problem in class incremental learning of EWC is solved, improving the model's ability to identify old categories and its overall accuracy.
CN117253111BActive Publication Date: 2026-06-09BEIHANG UNIV +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIHANG UNIV
- Filing Date
- 2023-09-07
- Publication Date
- 2026-06-09
Smart Images
Figure CN117253111B_ABST
Abstract
The application discloses a class-incremental continual learning method based on classification layer unification and improved EWC, a neural network is trained through a training set to obtain a recognition model, and the recognition model is used for recognizing the category of things in a picture, the training comprises old task training and at least one new task training, and in the new task retraining process, the model parameters of the old task are taken as a base point to limit the parameter offset. The class-incremental continual learning method based on classification layer unification and improved EWC solves the new category bias problem and improves the average accuracy of the model.
Need to check novelty before this filing date? Find Prior Art