Unsupervised object discovery: A comparison

Tinne Tuytelaars*, Christoph H. Lampert, Matthew B. Blaschko, Wray Buntine

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    149 Citations (Scopus)

    Abstract

    The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.

    Original languageEnglish
    Pages (from-to)284-302
    Number of pages19
    JournalInternational Journal of Computer Vision
    Volume88
    Issue number2
    DOIs
    Publication statusPublished - Jun 2010

    Fingerprint

    Dive into the research topics of 'Unsupervised object discovery: A comparison'. Together they form a unique fingerprint.

    Cite this