On Class Orderings for Incremental Learning

By Marc Masana, Bartłomiej Twardowski, Joost van de Weijer. 2020

17 citations recorded by the source corpus.

The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods.

Subfields: Artificial Intelligence, Meta & Continual Learning

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

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, neutral): “In contrast, the latest surveystypicallycollateonlyalocalaspectofcontinuallearning, withrespecttoitsbiologicalunderpinnings[1],[3],[9],[10], specializedsettingsforvisualclassiﬁcation[11],[12],[13],[14], andspeciﬁcextensionsforNLP[15],[16]orRL[17].”
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (2020, background): “Recently, [130] also brings attention to the learning variability between using different class orderings when learning a sequence of tasks incrementally.”