Journal article
A discriminative representation of convolutional features for indoor scene recognition
IEEE Transactions on Image Processing, Vol.25(7), pp.3372-3383
2016
Abstract
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.
Details
- Title
- A discriminative representation of convolutional features for indoor scene recognition
- Authors/Creators
- S.H. Khan (Author/Creator) - Commonwealth Scientific and Industrial Research OrganisationM. Hayat (Author/Creator) - University of CanberraM. Bennamoun (Author/Creator) - The University of Western AustraliaR. Togneri (Author/Creator) - The University of Western AustraliaF.A. Sohel (Author/Creator) - Murdoch University
- Publication Details
- IEEE Transactions on Image Processing, Vol.25(7), pp.3372-3383
- Publisher
- IEEE
- Identifiers
- 991005544569307891
- Copyright
- 2016 IEEE Signal Processing Society
- Murdoch Affiliation
- School of Engineering and Information Technology
- Language
- English
- Resource Type
- Journal article
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Metrics
70 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Citation topics
- 4 Electrical Engineering, Electronics & Computer Science
- 4.17 Computer Vision & Graphics
- 4.17.128 Deep Visual Recognition
- Web Of Science research areas
- Computer Science, Artificial Intelligence
- Engineering, Electrical & Electronic
- ESI research areas
- Engineering