Sign in

Machine learning and computer vision at the University of Cambridge (UK), PhD.

Hands-on Tutorials

Deep dive into full-reference image quality assessment. From subjective image quality experiments to deep objective image quality metrics.

Image by Author

From mean squared error to GANs — what makes a good perceptual loss function?

Image by the Author.

Image by Author

Image by author

Examples and code

Image by Author

Image by Author.
  • Vanishing gradient problem
  • Convergence speed
  • How to achieve invariance and equivariance
  • Removing artefacts caused by de-convolution
  • Loss functions for images-to-image translation
  • Ways of feeding in varied size images
  • How to take distant spatial relationships into account
  • More complex model extensions to CNNs

Tackling De-convolution

Image by Author.

Image by Author

Image by Author

What are we trying to solve?

Image by Author

Confidence intervals

Aliaksei Mikhailiuk

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store