Sorted Convolutional Network for Achieving Continuous Rotational Invariance
The topic of achieving rotational invariance in convolutional neural networks (CNNs) has gained considerable attention recently, as this invariance is crucial for many computer vision tasks such as image classification and matching. In this letter, we propose a Sorting Convolution (SC) inspired by some hand-crafted features of texture images, which achieves continuous rotational invariance without requiring additional learnable parameters or data augmentation. Further, SC can directly replace the conventional convolution operations in a classic CNN model to achieve its rotational invariance. Based on MNIST-rot dataset, we first analyze the impact of convolutional kernel sizes, different sampling and sorting strategies on SC's rotational invariance, and compare our method with previous rotation-invariant CNN models. Then, we combine SC with VGG, ResNet and DenseNet, and conduct classification experiments on popular texture and remote sensing image datasets. Our results demonstrate that SC achieves the best performance in the aforementioned tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Data Augmentationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting 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 ClassificationAchieving Rotational Invariance with Bessel-Convolutional Neural Networks
For many applications in image analysis, learning models that are invariant to translations and rotations is paramount. This is the case, for example, in medical imaging where the objects of interest can appear at arbitr…
Equivariance-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+1Rotation 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. …
ClassificationGeneral Classificationimage-classificationImage ClassificationSPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting
Translational invariance induced by pooling operations is an inherent property of convolutional neural networks, which facilitates numerous computer vision tasks such as classification. Yet to leverage rotational invaria…
Data AugmentationSolar Irradiance Forecasting