CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
It addresses the challenge of enabling robots to adapt continually with minimal data, which is crucial for real-world applications, though it appears incremental as it builds on existing cognitive-inspired methods.
The paper tackles the problem of Few-Shot class Incremental Learning (FSIL) for robots, where agents must learn new object classes from limited data without forgetting old ones, achieving state-of-the-art performance on object classification datasets and demonstrating continual learning on a robot with household objects.
For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification datasets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.