Learned transform compression with optimized entropy encoding

  • We consider the problem of learned transform compression where we learn both, the transform as well as the probability distribution over the discrete codes. We utilize a soft relaxation of the quantization operation to allow for back-propagation of gradients and employ vector (rather than scalar) quantization of the latent codes. Furthermore, we apply similar relaxation in the code probability assignments enabling direct optimization of the code entropy. To the best of our knowledge, this approach is completely novel. We conduct a set of proof-of concept experiments confirming the potency of our approaches.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Magda Gregorová, Marc Desaules, Alexandros Kalousis
Persistent identifier:https://openreview.net/forum?id=SmV8N_RbB_
Parent Title (English):Neural Compression Workshop (CoRR)
Document Type:Conference Proceeding
Language:English
Year of publication:2021
Release Date:2024/01/22
Volume:abs/2104.03305
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.