Offset equivariant networks and their applications
This addresses the issue of inconsistent network behavior under photometric transformations for applications in computer vision, though it appears incremental as it builds on existing equivariance concepts.
The paper tackles the problem of designing neural networks that maintain consistent performance under varying lighting conditions by introducing offset equivariant networks, which preserve uniform input increments and achieve comparable state-of-the-art results on tasks like image recognition, illuminant estimation, and image inpainting.
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.