[Paper Review] Group Equivariant Convolutional Networks

Taco Cohen, Max Welling|arXiv (Cornell University)|Feb 24, 2016

Advanced Neural Network Applications41 references584 citations

TL;DR

This paper generalizes CNNs to group equivariant convolutions (G-convolutions) for discrete symmetry groups (like p4 and p4m), achieving improved performance with no extra parameters and state-of-the-art results on rotated MNIST and CIFAR-10 with minimal overhead.

ABSTRACT

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 type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and rotations. G-CNNs achieve state of the art results on CIFAR10 and rotated MNIST.

Motivation & Objective

• Motivate and formalize the use of symmetry groups to improve data efficiency in deep networks.
• Introduce G-convolutions and show they share more weight‑sharing than standard convolutions while preserving expressivity.
• Demonstrate that G-CNNs achieve state-of-the-art results on rotated MNIST and CIFAR-10 with negligible computational overhead.
• Provide practical implementation guidance for G-convolutions and pooling for discrete groups.
• Discuss extensions and future directions for structured representations in neural networks.

Proposed method

• Define group actions and functions on groups to model feature maps as G-spaces.
• Introduce G-convolution (G-correlation) that operates over a group G, ensuring equivariance under G transformations.
• Show that nonlinearities and pooling can be designed to preserve equivariance (including coset pooling for G/H).
• Provide efficient implementation via filter transformation and planar convolution, enabling fast G-convolutions for split groups like p4 and p4m.
• Demonstrate that standard network components (batch norm, residual blocks) remain equivariant within G-CNNs.

Experimental results

Research questions

• RQ1 Can CNNs be generalized to be equivariant to larger symmetry groups beyond translations (e.g., rotations and reflections) without increasing parameter count?
• RQ2 Do G-convolutions, G-pooling, and nonlinearities preserve equivariance across layers, enabling deep G-CNNs?
• RQ3 Do G-CNNs yield practical performance gains on rotated or augmented datasets (MNIST-rot, CIFAR-10) compared to standard CNNs?
• RQ4 What are the practical considerations and efficiency costs when implementing G-convolutions for groups like p4 and p4m?
• RQ5 What extensions and future directions exist for applying G-CNNs to other groups or higher dimensions?

Key findings

• G-convolutions for discrete groups (p4, p4m) share substantially more weight across transformations, increasing expressive capacity without adding parameters.
• G-CNNs achieve state-of-the-art results on rotated MNIST: P4CNN reaches 2.28% test error, outperforming prior methods.
• On CIFAR-10 and augmented CIFAR-10+, G-CNNs with p4m yield strong results: ResNet44 with p4m achieves 6.46% and 4.94% respectively, and a wider 26-layer p4m network reaches 4.19% with augmentation (compared to 5.27% planar).
• Replacing planar convolutions with G-convolutions provides consistent improvements without extensive tuning.
• G-CNNs benefit from data augmentation similarly to standard CNNs, with improvements observed even when the dataset is not perfectly symmetric.