Saved in:
Bibliographic Details
Main Authors: Ghobrial, Abanoub, Eder, Kerstin
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.07461
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914626848948224
author Ghobrial, Abanoub
Eder, Kerstin
author_facet Ghobrial, Abanoub
Eder, Kerstin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_07461
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Self-Supervised Dynamic Incremental Regularised Adaptation
Ghobrial, Abanoub
Eder, Kerstin
Machine Learning
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.
title On Self-Supervised Dynamic Incremental Regularised Adaptation
topic Machine Learning
url https://arxiv.org/abs/2311.07461