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

Description

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, weconsider an algorithm consisting of the concatenation of transfer learning with clustering using Self-Organizing Maps (SOMs). We introducea TensorFlow-based implementation to speed-up the process in multicore CPUs and GPUs. Finally, we demonstrate the effectiveness of themethod using standard off-the-shelf few-shot classification benchmarks

Abstract

Paper ID: #337

Abstract

International audience

Additional details