arXiv Analytics

Sign in

arXiv:1805.06447 [cs.CV]AbstractReferencesReviewsResources

Spatial Transformer Introspective Neural Network

Yunhan Zhao, Ye Tian, Wei Shen, Alan Yuille

Published 2018-05-16Version 1

Natural images contain many variations such as illumination differences, affine transformations, and shape distortions. Correctly classifying these variations poses a long standing problem. The most commonly adopted solution is to build large-scale datasets that contain objects under different variations. However, this approach is not ideal since it is computationally expensive and it is hard to cover all variations in one single dataset. Towards addressing this difficulty, we propose the spatial transformer introspective neural network (ST-INN) that explicitly generates samples with the unseen affine transformation variations in the training set. Experimental results indicate ST-INN achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN and CIFAR-10. We further extend our method to cross dataset classification tasks and few-shot learning problems to verify our method under extreme conditions and observe substantial improvements from experiment results.

Related articles: Most relevant | Search more
arXiv:0806.1984 [cs.CV] (Published 2008-06-12)
Classification of curves in 2D and 3D via affine integral signatures
arXiv:1804.10855 [cs.CV] (Published 2018-04-28)
Evaluation of Feature Detector-Descriptor for Real Object Matching under Various Conditions of Ilumination and Affine Transformation
arXiv:1502.02160 [cs.CV] (Published 2015-02-07)
A Survey on Hough Transform, Theory, Techniques and Applications