Meta learning for unsupervised clustering

Han Ul Kim, Yeong Jun Koh, Chang Su Kim

Research output: Contribution to conferencePaperpeer-review


Learning an embedding space is essential in clustering. Deep learning has been used recently for this purpose, yielding impressive clustering results. However, it remains challenging to discover clusters in small data, which are insufficient to train deep networks. To address this challenge, we adopt the meta learning strategy, which learns to learn new tasks efficiently. We propose a novel meta learner, called MLC-Net, which mimics numerous clustering tasks during the training to learn an effective embedding space for new clustering tasks. MLC-Net has three building blocks: encoder, centroid, and prediction blocks. The encoder block transforms input patterns into an embedding space, while the centroid block estimates a representative feature for each cluster, called pseudo-centroid. It makes the embedding space more effective and more reliable, by learning an embedding space and a pseudo-centroid estimator jointly. Extensive experimental results on the Omniglot, MNIST, and Mini-ImageNet datasets demonstrate that MLC-Net achieves the state-of-the-art unsupervised clustering, as well as few-shot classification, performances.

Original languageEnglish
Publication statusPublished - 2020
Event30th British Machine Vision Conference, BMVC 2019 - Cardiff, United Kingdom
Duration: 2019 Sept 92019 Sept 12


Conference30th British Machine Vision Conference, BMVC 2019
Country/TerritoryUnited Kingdom

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Meta learning for unsupervised clustering'. Together they form a unique fingerprint.

Cite this