Deep Scale-spaces: Equivariance Over Scale
This addresses scale invariance for image recognition tasks, offering a plug-and-play method that is incremental as it builds on existing CNN architectures.
The paper tackled the problem of scale invariance in image recognition by introducing deep scale-spaces (DSS), a generalization of CNNs that exploits scale symmetry, resulting in demonstrated utility on Patch Camelyon and Cityscapes datasets.
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.