paper-with-me

홈 › Papers

Exploiting Learned Symmetries in Group Equivariant Convolutions

2021-06-09 · Attila Lengyel, Jan C. van Gemert

Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost. We investigate the filter parameters learned by GConvs and find certain conditions under which they become highly redundant. We show that GConvs can be efficiently decomposed into depthwise separable convolutions while preserving equivariance properties and demonstrate improved performance and data efficiency on two datasets. All code is publicly available at github.com/Attila94/SepGrouPy.

📄 PDF Abstract BibTeX arXiv:2106.04914

Code (1)

Attila94/SepGroupPy 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Group Equivariant Convolutional Networks

2016-02-24 · Taco S. Cohen, Max Welling

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new t…

Breast Tumour ClassificationColorectal Gland Segmentation:Multi-tissue Nucleus SegmentationRotated MNIST

Efficient Continuous Group Convolutions for Local SE(3) Equivariance in 3D Point Clouds

2025-02-11 · Lisa Weijler, Pedro Hermosilla

Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting a…

Semantic SegmentationTranslation

Symmetry From Scratch: Group Equivariance as a Supervised Learning Task

2024-10-05 · Haozhe Huang, Leo Kaixuan Cheng, Kaiwen Chen, Alán Aspuru-Guzik

In machine learning datasets with symmetries, the paradigm for backward compatibility with symmetry-breaking has been to relax equivariant architectural constraints, engineering extra weights to differentiate symmetries …

Inductive Bias

Current Symmetry Group Equivariant Convolution Frameworks for Representation Learning

2024-09-11 · Ramzan Basheer, Deepak Mishra

Euclidean deep learning is often inadequate for addressing real-world signals where the representation space is irregular and curved with complex topologies. Interpreting the geometric properties of such feature spaces h…

Deep LearningRepresentation Learning

SO(3)-Equivariant Neural Networks for Learning Vector Fields on Spheres

2025-03-12 · Francesco Ballerin, Nello Blaser, Erlend Grong

Analyzing vector fields on the sphere, such as wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetries of the sphere and the inherent symmetries of the vector fields. …