paper-with-me

홈 › Papers

Rotation Equivariance and Invariance in Convolutional Neural Networks

2018-05-31 · Benjamin Chidester, Minh N. Do, Jian Ma

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.

📄 PDF Abstract BibTeX arXiv:1805.12301

Code (2)

bchidest/RiCNN 공식 구현 tf
https://gitlab.com/exwzd-public/kiritani_ono_2020 pytorch

Tasks

ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Learnable Gabor modulated complex-valued networks for orientation robustness

2020-11-23 · Felix Richards, Adeline Paiement, Xianghua Xie, Elisabeth Sola 외

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 AugmentationTranslation

Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods

2019-10-31 · Luca Della Libera, Vladimir Golkov, Yue Zhu, Arman Mielke 외

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 Estimation

Rotation-Invariant Point Convolution With Multiple Equivariant Alignments

2020-12-07 · Hugues Thomas

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 Segmentation

Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks

2023-10-12 · Facundo Manuel Quiroga, Franco Ronchetti, Laura Lanzarini, Aurelio Fernandez-Bariviera

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 Classification

Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network

2021-06-18 · Sungwon Hwang, Hyungtae Lim, Hyun Myung

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