Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts

TL;DR

This paper introduces VP G-CNN, a novel neural network model that adaptively adjusts its equivariance to rotations and color shifts for each data instance, improving flexibility and robustness in real-world tasks.

Contribution

The paper proposes a variational approach to dynamically control partial equivariance levels in G-CNNs based on input data, addressing fixed symmetry limitations.

Findings

Effective on toy and real-world datasets

Improves adaptability to partial symmetries

Maintains robustness and uncertainty metrics

Abstract

Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of the whole group, limiting adaptability to diverse partial symmetries in real-world datasets, such as limited rotation symmetry of handwritten digit images and limited color-shift symmetry of flower images. Recent efforts address this limitation, one example being Partial G-CNN which restricts the output group space of convolution layers to break full equivariance. However, such an approach still fails to adjust equivariance levels across data. In this paper, we propose a novel approach, Variational Partial G-CNN (VP G-CNN), to capture varying levels of partial equivariance specific to each data instance. VP G-CNN redesigns the distribution of the output group elements to be conditioned on input data, leveraging variational inference to avoid overfitting. This enables the model to adjust its equivariance levels according to the needs of individual data points. Additionally, we address training instability inherent in discrete group equivariance models by redesigning the reparametrizable distribution. We demonstrate the effectiveness of VP G-CNN on both toy and real-world datasets, including MNIST67-180, CIFAR10, ColorMNIST, and Flowers102. Our results show robust performance, even in uncertainty metrics.