A convolution based ensembling technique to efficiently make use of various backbone CNN networks.

What is it about?

Over the past few years, there has been a significant improvement in the domain of few-shot learning. This learning paradigm has shown promising results for the challenging problem of anomaly detection, where the general task is to deal with heavy class imbalance. This paper presents a new approach to few-shot classification, where we employ the knowledge base of multiple pre-trained convolutional models that act as the backbone for our proposed few-shot framework. Our framework uses a novel ensembling technique for boosting the accuracy while drastically decreasing the total parameter count, thus paving the way for real-time implementation.

Featured Image

Photo by Andrew Ridley on Unsplash

Photo by Andrew Ridley on Unsplash

Why is it important?

This work introduces a new lightweight framework which reduces the computational cost while improving the previous state of the art results in the few shot learning domain.