English

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

Neural and Evolutionary Computing 2020-09-09 v1 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2009.03665,
  title  = {GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning},
  author = {Lyes Khacef and Vincent Gripon and Benoit Miramond},
  journal= {arXiv preprint arXiv:2009.03665},
  year   = {2020}
}

Comments

Accepted for publication in the International Conference on Neural Information Processing (ICONIP) 2020. arXiv admin note: text overlap with arXiv:2009.02174

R2 v1 2026-06-23T18:23:16.501Z