SCIENCE@home

Semi-Supervised Class Discovery

J. Nixon,J. Liu,David Berthelot

Published 2020 in arXiv.org

ABSTRACT

One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels can be deployed against an arbitrary amount of data, discovering classification schemes that through training create a higher quality representation of data. We introduce the Dataset Reconstruction Accuracy, a new and important measure of the effectiveness of a model's ability to create labels. We introduce benchmarks against this Dataset Reconstruction metric. We apply a new heuristic, class learnability, for deciding whether a class is worthy of addition to the training dataset. We show that our class discovery system can be successfully applied to vision and language, and we demonstrate the value of semi-supervised learning in automatically discovering novel classes.

PUBLICATION RECORD

  • Publication year

    2020

  • Venue

    arXiv.org

  • Publication date

    2020-02-10

  • Fields of study

    Mathematics, Computer Science

  • Identifiers
    arXiv 2002.03480
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

CONCEPTS

REFERENCES

Showing 1-45 of 45 references · Page 1 of 1

CITED BY