paper-with-me

Papers

Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)

2023-06-12 · Wei-Dong Qiao, Yang Xu, Hui Li

The weight-sharing mechanism of convolutional kernels ensures translation-equivariance of convolution neural networks (CNNs). Recently, rotation-equivariance has been investigated. However, research on scale-equivariance or simultaneous scale-rotation-equivariance is insufficient. This study proposes a Lie group-CNN, which can keep scale-rotation-equivariance for image classification tasks. The Lie group-CNN includes a lifting module, a series of group convolution modules, a global pooling layer, and a classification layer. The lifting module transfers the input image from Euclidean space to Lie group space, and the group convolution is parameterized through a fully connected network using Lie-algebra of Lie-group elements as inputs to achieve scale-rotation-equivariance. The Lie group SIM(2) is utilized to establish the Lie group-CNN with scale-rotation-equivariance. Scale-rotation-equivariance of Lie group-CNN is verified and achieves the best recognition accuracy on the blood cell dataset (97.50%) and the HAM10000 dataset (77.90%) superior to Lie algebra convolution network, dilation convolution, spatial transformer network, and scale-equivariant steerable network. In addition, the generalization ability of the Lie group-CNN on SIM(2) on rotation-equivariance is verified on rotated-MNIST and rotated-CIFAR10, and the robustness of the network is verified on SO(2) and SE(2). Therefore, the Lie group-CNN can successfully extract geometric features and performs equivariant recognition on images with rotation and scale transformations.

📄 PDF Abstract BibTeX arXiv:2306.06934

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationRotated MNIST

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Spatial Transformer A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a [convolutional neural…

Similar Papers 제목 키워드 기반

Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks

2018-07-02 · Jasper Linmans, Jim Winkens, Bastiaan S. Veeling, Taco S. Cohen 외

We propose a semantic segmentation model that exploits rotation and reflection symmetries. We demonstrate significant gains in sample efficiency due to increased weight sharing, as well as improvements in robustness to s…

DecoderSegmentationSemantic Segmentation

Affine Equivariant Networks Based on Differential Invariants

2024-01-01 · CVPR 2024 1 · Yikang Li, Yeqing Qiu, Yuxuan Chen, Lingshen He 외

Convolutional neural networks benefit from translation equivariance achieving tremendous success. Equivariant networks further extend this property to other transformation groups. However most existing methods requir…

RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks

2018-05-17 · ICLR 2019 5 · Xiuyuan Cheng, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper propos…

Rotational 3D Texture Classification Using Group Equivariant CNNs

2018-10-16 · Vincent Andrearczyk, Adrien Depeursinge

Convolutional Neural Networks (CNNs) traditionally encode translation equivariance via the convolution operation. Generalization to other transformations has recently received attraction to encode the knowledge of the da…

ClassificationDiversityGeneral ClassificationTexture Classification+1

SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms

2022-08-21 · Shuai Su, Zhongkai Zhao, Yixin Fei, Shuda Li 외

Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale…

Benchmarking