AgileNet: Lightweight Dictionary-based Few-shot Learning

TL;DR

AgileNet introduces a lightweight, dictionary-based few-shot learning method that enables efficient, adaptable neural networks on resource-constrained edge devices, outperforming prior approaches in accuracy and reducing complexity.

Contribution

It presents a novel end-to-end structured decomposition for dictionary learning that prevents model updates from primary training, reducing memory and computation for edge deployment.

Findings

Superior accuracy on few-shot benchmarks.

Reduces memory footprint and computational complexity.

Prevents knowledge loss from primary training during updates.

Abstract

The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to obtain the same inference capability on a resource-constrained device while providing adaptability to cope with the dynamic changes in the data. We propose AgileNet, a novel lightweight dictionary-based few-shot learning methodology which provides reduced complexity deep neural network for efficient execution at the edge while enabling low-cost updates to capture the dynamics of the new data. Evaluations of state-of-the-art few-shot learning benchmarks demonstrate the superior accuracy of AgileNet compared to prior arts. Additionally, AgileNet is the first few-shot learning approach that prevents model updates by eliminating the knowledge obtained from the primary training. This property is ensured through the dictionaries learned by our novel end-to-end structured decomposition, which also reduces the memory footprint and computation complexity to match the edge device constraints.