Clustering-based Domain-Incremental Learning

IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3376–3384

Abstract

We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic forgetting problem", in which the performance of the learner in an "old task" decreases when subsequently trained on a "new task". Existing continual learning methods, such as Averaged Gradient Episodic Memory (A-GEM) and Orthogonal Gradient Descent (OGD), address catastrophic forgetting by minimizing the loss for the current task without increasing the loss for previous tasks. However, these methods assume the learner knows when the task changes, which is unrealistic in practice. In this paper, we alleviate the need to provide the algorithm with information about task changes by using an online clustering-based approach on a dynamically updated finite pool of samples or gradients. We thereby successfully counteract catastrophic forgetting in one of the hardest settings, namely: domain-incremental learning, a setting for which the problem was previously unsolved. We showcase the benefits of our approach by applying these ideas to projection-based methods, such as A-GEM and OGD, which lead to task-agnostic versions of them. Experiments on real datasets demonstrate the effectiveness of the proposed strategy and its promising performance compared to state-of-the-art methods.

Authors 6

1. Christiaan Lamers

   NORCE Research AS

   Affiliation as printed

   NORCE,Grimstad,Norway,4879

2. René Vidal

   University of Pennsylvania

   Affiliation as printed

   University of Pennsylvania,Institute for Data Engineering and Science,Philadelphia,USA

   Institute for Data Engineering and Science, University of Pennsylvania, Philadelphia, USA

3. Nabil Belbachir

   NORCE Research AS

   Affiliation as printed

   NORCE,Grimstad,Norway,4879

4. Bas van Stein Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science,Leiden,The Netherlands,2333 CA

5. Thomas Bäck Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science,Leiden,The Netherlands,2333 CA

6. Paris V. Giampouras

   Johns Hopkins University

   Affiliation as printed

   Johns Hopkins University,Baltimore,MD,US,21218