Brain-Inspired Model for Incremental Learning Using a Few Examples

By Ali Ayub, Alan R. Wagner. 2020

3 citations recorded by the source corpus.

Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally. We propose a novel approach to incremental learning inspired by the concept learning model of the hippocampus that represents each image class as centroids and does not suffer from catastrophic forgetting. Classification of a test image is accomplished using the distance of the test image to the n closest centroids. We further demonstrate that our approach can incrementally learn from only a few examples per class. Evaluations of our approach on three class-incremental learning benchmarks: Caltech-101, CUBS-200-2011 and CIFAR-100 for incremental and few-shot incremental learning depict state-of-the-art results in terms of classification accuracy over all learned classes.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Liyuan Wang
2. Jun Zhu
3. Lanqing Hong
4. Chongxuan Li
5. Kuo Yang
6. Zhenguo Li
7. Xingxing Zhang
8. Hongwei Yan

Citations in the corpus

• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning (2021, background): “CL of limited supervised data Few-shot continual or incremental learning (FSIL) [10, 40, 3] incrementally learns new classes from a small amount of labeled data, which generally requires a pretraining step on large amounts of base tasks and training samples for few-shot generalization.”