2015/06/30 by Munawar Hayat, Salman H. Khan, Mohammed Bennamoun +1 · 70 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Contextual image classification #Convolutional neural network #Feature (linguistics) #Feature extraction #Image Retrieval and Classification Techniques #Invariant (physics) #Pattern recognition (psychology) #Robustness (evolution) #Scale (ratio) #Training set #cs.CV
paper · pdf · doi:10.1109/tip.2016.2599292
published in IEEE Transactions on Image Processing 25(10), 4829-4841 (Institute of Electrical and Electronics Engineers)
arxiv created 2015/08/14 · openalex created_date 2016/06/24 · openalex publication_date 2016/08/10 · arxiv updated 2016/11/03 · openalex updated_date 2026/08/05
Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Furthermore, these objects can be of varying sizes and are present across numerous spatial locations in different layouts. For automatic indoor scene categorization, large-scale spatial layout deformations and scale variations are therefore two major challenges and the design of rich feature descriptors which are robust to these challenges is still an open problem. This paper introduces a new learnable feature descriptor called “spatial layout and scale invariant convolutional activations” to deal with these challenges. For this purpose, a new convolutional neural network architecture is designed which incorporates a novel “spatially unstructured” layer to introduce robustness against spatial layout deformations. To achieve scale invariance, we present a pyramidal image representation. For feasible training of the proposed network for images of indoor scenes, this paper proposes a methodology, which efficiently adapts a trained network model (on a large-scale data) for our task with only a limited amount of available training data. The efficacy of the proposed approach is demonstrated through extensive experiments on a number of data sets, including MIT-67, Scene-15, Sports-8, Graz-02, and NYU data sets.