Learning Novel Objects Continually Through Curiosity
arXiv:2103.07758
Abstract
Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. The paper analyzes a recent state-of-the-art approach for continual learning. The paper further develops a self-supervised technique to find most of the uncertain objects in an environment by utilizing the cluster representation of the previously learned classes. We test our approach on a benchmark dataset for continual learning on robots. Our results show that our curiosity-driven continual learning approach beats random sampling and softmax-based uncertainty sampling in terms of classification accuracy and the total number of classes learned.
arXiv commentAccepted at IEEE ICRA 2021 (Workshop titled, Towards Curious Robots: Modern Approaches for Intrinsically-Motivated Intelligent Behavior)
References in corpus (5)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Cognitively-Inspired Model for Incremental Learning Using a Few Examples
- EEC: Learning to Encode and Regenerate Images for Continual Learning
- Centroid Based Concept Learning for RGB-D Indoor Scene Classification
- Storing Encoded Episodes as Concepts for Continual Learning