Human and DNN Classification Performance on Images With Quality Distortions

Volume: 16, Issue: 2, Pages: 1 - 17
Published: Mar 16, 2019
Abstract
Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high-quality image datasets, yet in practical applications the input images cannot be assumed to be of high quality. Modern deep neural networks (DNNs) have been shown to perform poorly on images affected by blur or noise distortions. In this work, we investigate whether...
Paper Details
Title
Human and DNN Classification Performance on Images With Quality Distortions
Published Date
Mar 16, 2019
Volume
16
Issue
2
Pages
1 - 17
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.