Blind domain adaptation with augmented extreme learning machine features

Muhammad Uzair, Ajmal Mian

    Research output: Contribution to journalArticle

    21 Citations (Scopus)

    Abstract

    In practical applications, the test data often have different distribution from the training data leading to suboptimal visual classification performance. Domain adaptation (DA) addresses this problem by designing classifiers that are robust to mismatched distributions. Existing DA algorithms use the unlabeled test data from target domain during training time in addition to the source domain data. However, target domain data may not always be available for training. We propose a blind DA algorithm that does not require target domain samples for training. For this purpose, we learn a global nonlinear extreme learning machine (ELM) model from the source domain data in an unsupervised fashion. The global ELM model is then used to initialize and learn class specific ELM models from the source domain data. During testing, the target domain features are augmented with the reconstructed features from the global ELM model. The resulting enriched features are then classified using the class specific ELM models based on minimum reconstruction error. Extensive experiments on 16 standard datasets show that despite blind learning, our method outperforms six existing state-of-the-art methods in cross domain visual recognition.

    Original languageEnglish
    Article number7404267
    Pages (from-to)651-660
    Number of pages10
    JournalIEEE Transactions on Cybernetics
    Volume47
    Issue number3
    DOIs
    Publication statusPublished - 1 Mar 2017

    Fingerprint Dive into the research topics of 'Blind domain adaptation with augmented extreme learning machine features'. Together they form a unique fingerprint.

  • Cite this