# Learning Novel Objects Continually Through Curiosity

arXiv: https://arxiv.org/abs/2103.07758 · HTML: https://mlsanity.com/paper/2103.07758/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 13 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [EEC: Learning to Encode and Regenerate Images for Continual Learning](https://mlsanity.com/paper/2101.04904/) (2021)
- [Tell me what this is: Few-Shot Incremental Object Learning by a Robot](https://mlsanity.com/paper/2008.00819/) (2020)
- [Learning to Caption Images through a Lifetime by Asking Questions](https://mlsanity.com/paper/1812.00235/) (2018)
- [Storing Encoded Episodes as Concepts for Continual Learning](https://mlsanity.com/paper/2007.06637/) (2020)
- [What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper](https://mlsanity.com/paper/2009.05105/) (2020)

## Built on by (most cited first, 2 of 2)

- [Few-Shot Continual Active Learning by a Robot](https://mlsanity.com/paper/2210.04137/) (2022)
- [Don't Forget to Buy Milk: Contextually Aware Grocery Reminder Household Robot](https://mlsanity.com/paper/2207.09050/) (2022)

## Abstract (arXiv)

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.