Rectification-based Knowledge Retention for Task Incremental Learning

Pratik Mazumder, Pravendra Singh, Piyush Rai, Vinay P. Namboodiri

Research output: Contribution to journalArticlepeer-review

Abstract

In the task incremental learning problem, deep learning models suffer from catastrophic forgetting of previously seen classes/tasks as they are trained on new classes/tasks. This problem becomes even harder when some of the test classes do not belong to the training class set, i.e., the task incremental generalized zero-shot learning problem. We propose a novel approach to address the task incremental learning problem for both the non zero-shot and zero-shot settings. Our proposed approach, called Rectification-based Knowledge Retention (RKR), applies weight rectifications and affine transformations for adapting the model to any task. During testing, our approach can use the task label information (task-aware) to quickly adapt the network to that task. We also extend our approach to make it task-agnostic so that it can work even when the task label information is not available during testing. Specifically, given a continuum of test data, our approach predicts the task and quickly adapts the network to the predicted task. We experimentally show that our proposed approach achieves state-of-the-art results on several benchmark datasets for both non zero-shot and zero-shot task incremental learning.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
DOIs
Publication statusE-pub ahead of print - 30 Nov 2022

Keywords

  • Continual Learning
  • Deep Learning
  • Generalized Zero-Shot Classification
  • Image Classification
  • Task Incremental Learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Rectification-based Knowledge Retention for Task Incremental Learning'. Together they form a unique fingerprint.

Cite this