A Discriminative Representation of Convolutional Features for Indoor Scene Recognition

Salman Khan, M. Hayat, Mohammed Bennamoun, Roberto Togneri, F.A. Sohel

    Research output: Contribution to journalArticle

    39 Citations (Scopus)

    Abstract

    © 1992-2012 IEEE. Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities that characterize such scenes. This paper presents a novel approach that exploits rich mid-level convolutional features to categorize indoor scenes. Traditional convolutional features retain the global spatial structure, which is a desirable property for general object recognition. We, however, argue that the structure-preserving property of the convolutional neural network activations is not of substantial help in the presence of large variations in scene layouts, e.g., in indoor scenes. We propose to transform the structured convolutional activations to another highly discriminative feature space. The representation in the transformed space not only incorporates the discriminative aspects of the target data set but also encodes the features in terms of the general object categories that are present in indoor scenes. To this end, we introduce a new large-scale data set of 1300 object categories that are commonly present in indoor scenes. Our proposed approach achieves a significant performance boost over the previous state-of-The-Art approaches on five major scene classification data sets.
    Original languageEnglish
    Pages (from-to)3372-3383
    JournalIEEE Transactions on Image Processing
    Volume25
    Issue number7
    Early online date11 May 2016
    DOIs
    Publication statusPublished - Jul 2016

      Fingerprint

    Cite this