GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning
This addresses few-shot classification for edge devices where data labeling is infrequent, but it is incremental as it builds on existing methods.
The paper tackles post-labeled few-shot unsupervised learning by combining transfer learning with Self-Organizing Maps (SOMs) and introduces a GPU-based TensorFlow implementation, demonstrating effectiveness on standard benchmarks.
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.