The Informaticists

A take on the science of information

Menu

Skip to content
  • About
    • EE 376A
    • EE 25N
      • EE 25N Speakers
  • Podcast
  • Blog
    • Online Lectures
    • Information Theory (Winter 2021)
    • Information Theory (Winter 2020)
    • Information Theory (Winter 2019)
    • Journal for High Schoolers
  • Outreach

Some very special high schoolers

EE 25N Speakers

Ashutosh Bhown, Soham Mukherjee, Sean Yang

TALK TITLE

Humans are awesome*

* lossy image compressors

TALK ABSTRACT

Lossy image compression has been studied extensively in the context of typical loss functions such as RMSE, MS-SSIM, etc. However, it is not well understood what loss function might be most appropriate for human perception. Furthermore, the availability of massive public image datasets appears to have hardly been exploited in image compression. In this work, we perform compression experiments in which one human describes images to another, using publicly available images and text instructions. These image reconstructions are rated by human scorers on the Amazon Mechanical Turk platform and compared to reconstructions obtained by existing image compressors. In our experiments, the humans outperform the state of the art compressor WebP in the MTurk survey on most images, which shows that there is significant room for improvement in image compression for human perception.

Post navigation

← Ziv Goldfeld
Widgets
Powered by WordPress.com.