Transform-invariant convolutional neural networks for image classification and search

Publication Type:
Conference Proceeding
MM 2016 - Proceedings of the 2016 ACM Multimedia Conference, 2016, pp. 1345 - 1354
Issue Date:
Filename Description Size
p1345-shen.pdfPublished version6.77 MB
Adobe PDF
Full metadata record
© 2016 ACM. Convolutional neural networks (CNNs) have achieved stateof-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transforminvariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval.
Please use this identifier to cite or link to this item: