GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning

TL;DR

This paper introduces a GPU-accelerated method combining transfer learning and Self-Organizing Maps for post-labeled few-shot unsupervised classification, suitable for edge devices with limited labeled data.

Contribution

It presents a novel GPU-based implementation of SOMs integrated with transfer learning for efficient post-labeled few-shot unsupervised learning.

Findings

Effective on standard few-shot benchmarks

Significant speed-up with GPU implementation

Applicable to edge device data acquisition

Abstract

Few-shot classification is a challenge in machine learning where the goal is to train a classifier using a very limited number of labeled examples. This scenario is likely to occur frequently in real life, for example when data acquisition or labeling is expensive. In this work, we consider the problem of post-labeled few-shot unsupervised learning, a classification task where representations are learned in an unsupervised fashion, to be later labeled using very few annotated examples. We argue that this problem is very likely to occur on the edge, when the embedded device directly acquires the data, and the expert needed to perform labeling cannot be prompted often. To address this problem, we consider an algorithm consisting of the concatenation of transfer learning with clustering using Self-Organizing Maps (SOMs). We introduce a TensorFlow-based implementation to speed-up the process in multi-core CPUs and GPUs. Finally, we demonstrate the effectiveness of the method using standard off-the-shelf few-shot classification benchmarks.