Parallel Neural Local Lossless Compression

Code

• github.com/zmtomorrow/parallelnelloc
  OfficialIn paperpytorch★ 13
• github.com/zmtomorrow/nelloc
  pytorch★ 13

Abstract

The recently proposed Neural Local Lossless Compression (NeLLoC), which is based on a local autoregressive model, has achieved state-of-the-art (SOTA) out-of-distribution (OOD) generalization performance in the image compression task. In addition to the encouragement of OOD generalization, the local model also allows parallel inference in the decoding stage. In this paper, we propose two parallelization schemes for local autoregressive models. We discuss the practicalities of implementing the schemes and provide experimental evidence of significant gains in compression runtime compared to the previous, non-parallel implementation.

Tasks

Reproductions