LLEDA – Lifelong Self-Supervised Domain Adaptation

11/12/2022
by   Mamatha Thota, et al.
9

Lifelong domain adaptation remains a challenging task in machine learning due to the differences among the domains and the unavailability of historical data. The ultimate goal is to learn the distributional shifts while retaining the previously gained knowledge. Inspired by the Complementary Learning Systems (CLS) theory, we propose a novel framework called Lifelong Self-Supervised Domain Adaptation (LLEDA). LLEDA addresses catastrophic forgetting by replaying hidden representations rather than raw data pixels and domain-agnostic knowledge transfer using self-supervised learning. LLEDA does not access labels from the source or the target domain and only has access to a single domain at any given time. Extensive experiments demonstrate that the proposed method outperforms several other methods and results in a long-term adaptation, while being less prone to catastrophic forgetting when transferred to new domains.

READ FULL TEXT

page 5

page 6

research
04/28/2023

AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain

This paper presents an unsupervised domain adaptation (UDA) method for p...
research
03/26/2021

Contrastive Domain Adaptation

Recently, contrastive self-supervised learning has become a key componen...
research
07/24/2020

Self-Supervised Learning Across Domains

Human adaptability relies crucially on learning and merging knowledge fr...
research
04/19/2021

DANICE: Domain adaptation without forgetting in neural image compression

Neural image compression (NIC) is a new coding paradigm where coding cap...
research
01/18/2021

Studying Catastrophic Forgetting in Neural Ranking Models

Several deep neural ranking models have been proposed in the recent IR l...
research
10/04/2018

Transferring Physical Motion Between Domains for Neural Inertial Tracking

Inertial information processing plays a pivotal role in ego-motion aware...
research
03/23/2022

Generic network for domain adaptation based on self-supervised learning and deep clustering

Domain adaptation methods train a model to find similar feature represen...

Please sign up or login with your details

Forgot password? Click here to reset