Importance Driven Continual Learning for Segmentation Across Domains

By Sinan Özgür Özgün, Anne-Marie Rickmann, Abhijit Guha Roy, Christian Wachinger. 2020

36 citations recorded by the source corpus.

The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones, i.e., they suffer from Catastrophic Forgetting (CF). The objective of Continual Learning (CL) is to alleviate this problem, which is particularly relevant for medical applications, where it may not be feasible to store and access previously used sensitive patient data. In this work, we propose a Continual Learning approach for brain segmentation, where a single network is consecutively trained on samples from different domains. We build upon an importance driven approach and adapt it for medical image segmentation. Particularly, we introduce learning rate regularization to prevent the loss of the network's knowledge. Our results demonstrate that directly restricting the adaptation of important network parameters clearly reduces Catastrophic Forgetting for segmentation across domains.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jun Liu
  2. Hossein Rahmani
  3. Li Xu
  4. Bryan M. Williams
  5. Haoxuan Qu
  6. G. Wang
  7. Amir Shahroudy
  8. Ajmal Saeed Mian

In Computer Vision and Pattern Recognition

  1. Hossein Rahmani
  2. Jun Liu
  3. Li Xu
  4. Bryan M. Williams
  5. Haoxuan Qu
  6. G. Wang
  7. Amir Shahroudy
  8. Ajmal Saeed Mian

Citations in the corpus