Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

TL;DR

This paper introduces WARSHIP, a brain-inspired computing framework for image super resolution, combining durable deep learning components and biological insights to balance speed and performance.

Contribution

It summarizes five durable deep learning components for vision, introduces WARSHIP as a new framework, and demonstrates its application in image super resolution with WARSHIP-XZNet.

Findings

WARSHIP components enhance vision models' durability

WARSHIP-XZNet achieves a good balance between speed and accuracy

Biological insights inform the design of brain-inspired computing models

Abstract

Evolution of deep learning shows that some algorithmic tricks are more durable , while others are not. To the best of our knowledge, we firstly summarize 5 more durable and complete deep learning components for vision, that is, WARSHIP. Moreover, we give a biological overview of WARSHIP, emphasizing brain-inspired computing of WARSHIP. As a step towards WARSHIP, our case study of image super resolution combines 3 components of RSH to deploy a CNN model of WARSHIP-XZNet, which performs a happy medium between speed and performance.