Few-Shot Continual Active Learning by a Robot

by   Ali Ayub, et al.
University of Waterloo
Penn State University

In this paper, we consider a challenging but realistic continual learning (CL) problem, Few-Shot Continual Active Learning (FoCAL), where a CL agent is provided with unlabeled data for a new or a previously learned task in each increment and the agent only has limited labeling budget available. Towards this, we build on the continual learning and active learning literature and develop a framework that can allow a CL agent to continually learn new object classes from a few labeled training examples. Our framework represents each object class using a uniform Gaussian mixture model (GMM) and uses pseudo-rehearsal to mitigate catastrophic forgetting. The framework also uses uncertainty measures on the Gaussian representations of the previously learned classes to find the most informative samples to be labeled in an increment. We evaluate our approach on the CORe-50 dataset and on a real humanoid robot for the object classification task. The results show that our approach not only produces state-of-the-art results on the dataset but also allows a real robot to continually learn unseen objects in a real environment with limited labeling supervision provided by its user.


page 14

page 15


Prototype Reminding for Continual Learning

Continual learning is a critical ability of continually acquiring and tr...

Online Learning of Objects through Curiosity-Driven Active Learning

Children learn continually by asking questions about the concepts they a...

Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition

Imaging in clinical routine is subject to changing scanner protocols, ha...

Active Class Selection for Few-Shot Class-Incremental Learning

For real-world applications, robots will need to continually learn in th...

Please sign up or login with your details

Forgot password? Click here to reset