Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS

Abstract: 

Deep hierarchical models for feature learning have emerged as an effective technique for object representation and classification in recent years. Though the features learnt using deep models have shown lot of promise towards achieving invariance to data transformations, this primarily comes at the expense of using much larger training data and model size. In the proposed work we devise a novel technique to incorporate rotation invariance, while training the deep model parameters. The convolution weight parameters in the network architecture are constrained to exhibit circular symmetry resulting in ``rotation equivariance'' of output feature maps. Rotation invariance is further achieved by max-pooling of the feature maps later in the hierarchy. We also show that by incorporating circular symmetry constraint into the training loss function, rotation invariance can be achieved with-in deep neural network framework with much lesser training data and model parameters. Our experiment results evaluated on rotated MNIST dataset further objectively validate the contribution.

up
0 users have voted:

Paper Details

Authors:
Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer
Submitted On:
28 February 2017 - 11:56pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Viswanath Gopalakrishnan
Paper Code:
2415
Document Year:
2017
Cite

Document Files

main.pdf

(700)

Subscribe

[1] Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer, "LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1529. Accessed: Oct. 14, 2019.
@article{1529-17,
url = {http://sigport.org/1529},
author = {Dhruv Kohli; Biplab Ch Das; Viswanath Gopalakrishnan; Kiran Nanjunda Iyer },
publisher = {IEEE SigPort},
title = {LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS},
year = {2017} }
TY - EJOUR
T1 - LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS
AU - Dhruv Kohli; Biplab Ch Das; Viswanath Gopalakrishnan; Kiran Nanjunda Iyer
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1529
ER -
Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer. (2017). LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS. IEEE SigPort. http://sigport.org/1529
Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer, 2017. LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS. Available at: http://sigport.org/1529.
Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer. (2017). "LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS." Web.
1. Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer. LEARNING ROTATION INVARIANCE IN DEEP HIERARCHIES USING CIRCULAR SYMMETRIC FILTERS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1529