Authors:
Shikha Gupta
1
;
Deepak Kumar Pradhan
2
;
Dileep Aroor Dinesh
1
and
Veena Thenkanidiyoor
2
Affiliations:
1
Indian Institute of Technology Mandi, India
;
2
National Institute of Technology Goa, India
Keyword(s):
Scene Classification, Dynamic Kernel, Set of Varying Length Feature Map, Support Vector Machine, Convolutional Neural Network, Deep Spatial Pyramid Match Kernel.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Computer Vision, Visualization and Computer Graphics
;
Image Understanding
;
Kernel Methods
;
Pattern Recognition
;
Theory and Methods
Abstract:
Several works have shown that Convolutional Neural Networks (CNNs) can be easily adapted to different
datasets and tasks. However, for extracting the deep features from these pre-trained deep CNNs a fixedsize
(e.g., 227227) input image is mandatory. Now the state-of-the-art datasets like MIT-67 and SUN-397
come with images of different sizes. Usage of CNNs for these datasets enforces the user to bring different
sized images to a fixed size either by reducing or enlarging the images. The curiosity is obvious that “Isn’t
the conversion to fixed size image is lossy ?”. In this work, we provide a mechanism to keep these lossy fixed
size images aloof and process the images in its original form to get set of varying size deep feature maps,
hence being lossless. We also propose deep spatial pyramid match kernel (DSPMK) which amalgamates set
of varying size deep feature maps and computes a matching score between the samples. Proposed DSPMK
act as a dynamic kernel in the classificat
ion framework of scene dataset using support vector machine. We
demonstrated the effectiveness of combining the power of varying size CNN-based set of deep feature maps
with dynamic kernel by achieving state-of-the-art results for high-level visual recognition tasks such as scene
classification on standard datasets like MIT67 and SUN397.
(More)