SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.03305 · ICLR · 2021

Learned transform compression with optimized entropy encoding

Magda Gregorová, Marc Desaules, Alexandros Kalousis

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.03305")
get_code_for_paper("2104.03305")
have("2104.03305")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.03305.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.03305.svg)](https://syntology.ai/paper/2104.03305)

Connect an agent — have() is free.