Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters

Abstract

Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a scaling-translation-equivariant (ST-equivariant) CNN with joint convolutions across the space and the scaling group, which is shown to be both sufficient and necessary to achieve equivariance for the regular representation of the scaling-translation group ST . To reduce the model complexity and computational burden, we decompose the convolutional filters under two pre-fixed separable bases and truncate the expansion to low-frequency components. A further benefit of the truncated filter expansion is the improved deformation robustness of the equivariant representation, a property which is theoretically analyzed and empirically verified. Numerical experiments demonstrate that the proposed scaling-translation-equivariant network with decomposed convolutional filters (ScDCFNet) achieves significantly improved performance in multiscale image classification and better interpretability than regular CNNs at a reduced model size.

References in corpus (16)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Improved Regularization of Convolutional Neural Networks with Cutout
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Spherical CNNs
• Locally Scale-Invariant Convolutional Neural Networks
• Scale-Invariant Convolutional Neural Networks
• General $E(2)$-Equivariant Steerable CNNs
• Selective Kernel Networks
• 3D G-CNNs for Pulmonary Nodule Detection
• Deep Scale-spaces: Equivariance Over Scale
• Scale equivariance in CNNs with vector fields
• DCFNet: Deep Neural Network with Decomposed Convolutional Filters
• Scale Steerable Filters for Locally Scale-Invariant Convolutional Neural Networks

Cited by in corpus (3)

• ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
• Deformation Robust Roto-Scale-Translation Equivariant CNNs
• Do CNNs Encode Data Augmentations?