no code implementations • 13 Nov 2023 • Abanoub Ghobrial, Kerstin Eder
In this paper, we give an overview of a recently developed method for dynamic domain adaptation, named DIRA, which relies on a few samples in addition to a regularisation approach, named elastic weight consolidation, to achieve state-of-the-art (SOTA) domain adaptation results.
no code implementations • 18 May 2023 • Abanoub Ghobrial, Samuel Budgett, Dieter Balemans, Hamid Asgari, Phil Reiter, Kerstin Eder
There is a lot of ongoing research effort into developing different techniques for neural networks compression.
1 code implementation • 21 Jan 2023 • Abanoub Ghobrial, Darryl Hond, Hamid Asgari, Kerstin Eder
Due to the black box nature of deep neural networks (DNN), the continuous validation of DNN during operation is challenging with the absence of a human monitor.
1 code implementation • 30 Apr 2022 • Abanoub Ghobrial, Xuan Zheng, Darryl Hond, Hamid Asgari, Kerstin Eder
We show that DIRA improves on the problem of forgetting and achieves strong gains in performance when retraining using a few samples from the target domain.