Cognitively-Inspired Model for Incremental Learning Using a Few Examples

Abstract

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, while most incremental learning approaches require a large amount of training data per class. We examine the problem of incremental learning using only a few training examples, referred to as Few-Shot Incremental Learning (FSIL). To solve this problem, we propose a novel approach inspired by the concept learning model of the hippocampus and the neocortex that represents each image class as centroids and does not suffer from catastrophic forgetting. We evaluate our approach on three class-incremental learning benchmarks: Caltech-101, CUBS-200-2011 and CIFAR-100 for incremental and few-shot incremental learning and show that our approach achieves state-of-the-art results in terms of classification accuracy over all learned classes.

arXiv commentAdded link to the code in the paper

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Progressive Neural Networks
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• FearNet: Brain-Inspired Model for Incremental Learning
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Centroid Based Concept Learning for RGB-D Indoor Scene Classification
• DeeSIL: Deep-Shallow Incremental Learning

Cited by in corpus (14)

• EEC: Learning to Encode and Regenerate Images for Continual Learning
• Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes
• Tell me what this is: Few-Shot Incremental Object Learning by a Robot
• Few-Shot Incremental Learning with Continually Evolved Classifiers
• Centroid Based Concept Learning for RGB-D Indoor Scene Classification
• What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper
• Storing Encoded Episodes as Concepts for Continual Learning
• Continual Learning through Human-Robot Interaction: Human Perceptions of a Continual Learning Robot in Repeated Interactions
• F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning
• Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning
• CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
• Few-shot Continual Learning: a Brain-inspired Approach
• Teach Me What You Want to Play: Learning Variants of Connect Four through Human-Robot Interaction
• Learning Novel Objects Continually Through Curiosity