Group Equivariant Generative Adversarial Networks

Abstract

Recent improvements in generative adversarial visual synthesis incorporate real and fake image transformation in a self-supervised setting, leading to increased stability and perceptual fidelity. However, these approaches typically involve image augmentations via additional regularizers in the GAN objective and thus spend valuable network capacity towards approximating transformation equivariance instead of their desired task. In this work, we explicitly incorporate inductive symmetry priors into the network architectures via group-equivariant convolutional networks. Group-convolutions have higher expressive power with fewer samples and lead to better gradient feedback between generator and discriminator. We show that group-equivariance integrates seamlessly with recent techniques for GAN training across regularizers, architectures, and loss functions. We demonstrate the utility of our methods for conditional synthesis by improving generation in the limited data regime across symmetric imaging datasets and even find benefits for natural images with preferred orientation.

arXiv commentAccepted by the International Conference on Learning Representations (ICLR) 2021

References in corpus (31)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Which Training Methods for GANs do actually Converge?
• The relativistic discriminator: a key element missing from standard GAN
• Group Equivariant Convolutional Networks
• cGANs with Projection Discriminator
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
• General $E(2)$-Equivariant Steerable CNNs
• Scattering Networks for Hybrid Representation Learning
• LOGAN: Latent Optimisation for Generative Adversarial Networks
• Prescribed Generative Adversarial Networks
• Lipschitz Generative Adversarial Nets
• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• Small-GAN: Speeding Up GAN Training Using Core-sets
• Attentive Group Equivariant Convolutional Networks
• Theoretical Aspects of Group Equivariant Neural Networks
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Smoothness and Stability in GANs
• Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology

Cited by in corpus (2)

• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology