Header

UZH-Logo

Maintenance Infos

Learning rotation invariant convolutional filters for texture classification


Marcos, Diego; Volpi, Michele; Tuia, Devis (2016). Learning rotation invariant convolutional filters for texture classification. In: 23rd International Conference on Pattern Recognition, Cancún (México), 4 December 2016 - 8 December 2016, 1-6.

Abstract

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to the state-of-the-art. Compared to standard shallow CNNs, the proposed method obtains higher classification performance while reducing by an order of magnitude the number of parameters to be learned.

Abstract

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to the state-of-the-art. Compared to standard shallow CNNs, the proposed method obtains higher classification performance while reducing by an order of magnitude the number of parameters to be learned.

Statistics

Downloads

2 downloads since deposited on 14 Feb 2017
2 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:8 December 2016
Deposited On:14 Feb 2017 09:18
Last Modified:30 Aug 2017 22:18
Publisher:arXiv
Free access at:Official URL. An embargo period may apply.
Official URL:https://arxiv.org/pdf/1604.06720v2
Related URLs:https://iapr.papercept.net/conferences/conferences/ICPR16/program/ICPR16_ContentListWeb_3.html (Organisation)

Download

Preview Icon on Download
Content: Published Version
Language: English
Filetype: PDF - Registered users only
Size: 1MB