Scale-covariant and scale-invariant Gaussian derivative networks

11/30/2020
by   Tony Lindeberg, et al.
0

This article presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNISTLargeScale dataset, which contains rescaled images from original MNIST over a factor 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.

READ FULL TEXT
research
06/11/2021

Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales

The ability to handle large scale variations is crucial for many real wo...
research
04/03/2020

Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges

The ability to handle large scale variations is crucial for many real wo...
research
05/29/2019

Provably scale-covariant hierarchical continuous networks based on scale-normalized differential expressions coupled in cascade

This article presents a theory for constructing continuous hierarchical ...
research
03/01/2019

Provably scale-covariant networks from oriented quasi quadrature measures in cascade

This article presents a continuous model for hierarchical networks based...
research
03/02/2023

Deep Neural Networks with Efficient Guaranteed Invariances

We address the problem of improving the performance and in particular th...
research
11/30/2014

Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-poo...
research
07/31/2018

Scale equivariance in CNNs with vector fields

We study the effect of injecting local scale equivariance into Convoluti...

Please sign up or login with your details

Forgot password? Click here to reset