DeepAI AI Chat
Log In Sign Up

Dynamic memory to alleviate catastrophic forgetting in continuous learning settings

07/06/2020
by   Johannes Hofmanninger, et al.
MedUni Wien
0

In medical imaging, technical progress or changes in diagnostic procedures lead to a continuous change in image appearance. Scanner manufacturer, reconstruction kernel, dose, other protocol specific settings or administering of contrast agents are examples that influence image content independent of the scanned biology. Such domain and task shifts limit the applicability of machine learning algorithms in the clinical routine by rendering models obsolete over time. Here, we address the problem of data shifts in a continuous learning scenario by adapting a model to unseen variations in the source domain while counteracting catastrophic forgetting effects. Our method uses a dynamic memory to facilitate rehearsal of a diverse training data subset to mitigate forgetting. We evaluated our approach on routine clinical CT data obtained with two different scanner protocols and synthetic classification tasks. Experiments show that dynamic memory counters catastrophic forgetting in a setting with multiple data shifts without the necessity for explicit knowledge about when these shifts occur.

READ FULL TEXT
04/13/2023

CoSDA: Continual Source-Free Domain Adaptation

Without access to the source data, source-free domain adaptation (SFDA) ...
03/24/2023

Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions

Deep neural networks for scene perception in automated vehicles achieve ...
04/29/2020

Reducing catastrophic forgetting with learning on synthetic data

Catastrophic forgetting is a problem caused by neural networks' inabilit...
09/28/2019

On Generalizing Detection Models for Unconstrained Environments

Object detection has seen tremendous progress in recent years. However, ...
11/11/2021

Lifelong Learning from Event-based Data

Lifelong learning is a long-standing aim for artificial agents that act ...
01/27/2020

Uncertainty-based Modulation for Lifelong Learning

The creation of machine learning algorithms for intelligent agents capab...
04/12/2018

Combating catastrophic forgetting with developmental compression

Generally intelligent agents exhibit successful behavior across problems...