Deep Scale-spaces: Equivariance Over Scale

05/28/2019
by   Daniel E. Worrall, et al.
5

We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks. Put plainly, the class of an image is invariant to the scale at which it is viewed. We construct scale equivariant cross-correlations based on a principled extension of convolutions, grounded in the theory of scale-spaces and semigroups. As a very basic operation, these cross-correlations can be used in almost any modern deep learning architecture in a plug-and-play manner. We demonstrate our networks on the Patch Camelyon and Cityscapes datasets, to prove their utility and perform introspective studies to further understand their properties.

READ FULL TEXT
research
09/01/2018

Evaluation of Neural Networks for Image Recognition Applications: Designing a 0-1 MILP Model of a CNN to create adversarials

Image Recognition is a central task in computer vision with applications...
research
08/16/2018

Anatomy Of High-Performance Deep Learning Convolutions On SIMD Architectures

Convolution layers are prevalent in many classes of deep neural networks...
research
12/23/2014

Deep Networks With Large Output Spaces

Deep neural networks have been extremely successful at various image, sp...
research
10/21/2019

Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks

Very deep convolutional neural networks (CNNs) have been firmly establis...
research
12/24/2021

Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures

The manuscript describes fast and scalable architectures and associated ...
research
04/05/2016

Deep Cross Residual Learning for Multitask Visual Recognition

Residual learning has recently surfaced as an effective means of constru...
research
06/24/2018

Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences

Recommendation systems based on image recognition could prove a vital to...

Please sign up or login with your details

Forgot password? Click here to reset