Rotation Equivariance and Invariance in Convolutional Neural Networks
Performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Many image classification tasks, such as those related to cellular imaging, exhibit invariance to rotation. We present a novel scheme using the magnitude response of the 2D-discrete-Fourier transform (2D-DFT) to encode rotational invariance in neural networks, along with a new, efficient convolutional scheme for encoding rotational equivariance throughout convolutional layers. We implemented this scheme for several image classification tasks and demonstrated improved performance, in terms of classification accuracy, time required to train the model, and robustness to hyperparameter selection, over a standard CNN and another state-of-the-art method.
Code (2)
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Learnable Gabor modulated complex-valued networks for orientation robustness
Robustness to transformation is desirable in many computer vision tasks, given that input data often exhibits pose variance. While translation invariance and equivariance is a documented phenomenon of CNNs, sensitivity t…
Data AugmentationTranslationDeep Learning for 2D and 3D Rotatable Data: An Overview of Methods
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance unde…
Motion EstimationRotation-Invariant Point Convolution With Multiple Equivariant Alignments
Recent attempts at introducing rotation invariance or equivariance in 3D deep learning approaches have shown promising results, but these methods still struggle to reach the performances of standard 3D neural networks. I…
Deep LearningSemantic SegmentationRevisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks
Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image tr…
Data Augmentationimage-classificationImage ClassificationEquivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less de…
Data Augmentationimage-classificationImage ClassificationRepresentation Learning+1