On Self-Supervised Dynamic Incremental Regularised Adaptation
This is an incremental improvement for domain adaptation in machine learning, addressing the label dependency issue in existing methods.
The paper tackles the limitation of a dynamic domain adaptation method (DIRA) requiring labeled samples by proposing a self-supervised modification to remove the need for labels, with experimental evaluation planned for future work.
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. DIRA has been previously shown to perform competitively with SOTA unsupervised adaption techniques. However, a limitation of DIRA is that it relies on labels to be provided for the few samples used in adaption. This makes it a supervised technique. In this paper, we propose a modification to the DIRA method to make it self-supervised i.e. remove the need for providing labels. Our proposed approach will be evaluated experimentally in future work.