Offset equivariant networks and their applications

TL;DR

This paper introduces offset equivariant networks that maintain consistent output behavior under uniform input shifts, demonstrating robustness across image recognition, illuminant estimation, and inpainting tasks.

Contribution

The paper presents a novel framework for designing offset equivariant neural networks that are robust to lighting changes, extending equivariance concepts to photometric transformations.

Findings

Comparable performance to state-of-the-art on standard data

Maintain consistent behavior under lighting changes

Effective in image recognition, illuminant estimation, and inpainting

Abstract

In this paper we present a framework for the design and implementation of offset equivariant networks, that is, neural networks that preserve in their output uniform increments in the input. In a suitable color space this kind of networks achieves equivariance with respect to the photometric transformations that characterize changes in the lighting conditions. We verified the framework on three different problems: image recognition, illuminant estimation, and image inpainting. Our experiments show that the performance of offset equivariant networks are comparable to those in the state of the art on regular data. Differently from conventional networks, however, equivariant networks do behave consistently well when the color of the illuminant changes.