Search Results for author:
Found 4 papers, 3 papers with code
Overcoming Generic Knowledge Loss with Selective Parameter Update
Our method achieves improvements on the accuracy of the newly learned tasks up to 7% while preserving the pretraining knowledge with a negligible decrease of 0. 9% on a representative control set accuracy.
Continual Zero-Shot Learning through Semantically Guided Generative Random Walks
The GRW loss augments the training by continually encouraging the model to generate realistic and characterized samples to represent the unseen space.
A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning
With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed.
Domain-Aware Continual Zero-Shot Learning
Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
