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

2018/10/03 by Wendi Xu, Ming Zhang, Xu, Wendi +1 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Advanced Image Processing Techniques #Artificial Intelligence (cs.AI) #Artificial intelligence #Cell Image Analysis Techniques #Component (thermodynamics) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deep learning #FOS: Computer and information sciences #Geology #High resolution #Image (mathematics) #Image Processing Techniques and Applications #Physics #Remote sensing #Resolution (logic) #Superresolution #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.1810.01620

published in arXiv (Cornell University) (Cornell University) · 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems

arxiv created 2018/10/03 · openalex publication_date 2018/10/03 · arxiv updated 2018/10/04 · openalex created_date 2018/10/12 · openalex updated_date 2026/08/08

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.

Citations

• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• Wavelet Convolutional Neural Networks for Texture Classification
• Image Super-Resolution Using Deep Convolutional Networks
• Deeply-Recursive Convolutional Network for Image Super-Resolution
• Accelerating the Super-Resolution Convolutional Neural Network
• Accurate Image Super-Resolution Using Very Deep Convolutional Networks

Related

• Deep Image: Scaling up Image Recognition
• A Fully Progressive Approach to Single-Image Super-Resolution
• Integration and Performance Analysis of Artificial Intelligence and Computer Vision Based on Deep Learning Algorithms
• Human Vision Constrained Super-Resolution
• Enhance the Image: Super Resolution using Artificial Intelligence in MRI