论文标题
平行神经局部无损压缩
Parallel Neural Local Lossless Compression
论文作者
论文摘要
最近提出的基于局部自回归模型的神经局部无损压缩（NELLOC）已在图像压缩任务中实现了最新的（SOTA）分布（OOD）概括性能。除了鼓励OOD泛化外，局部模型还允许在解码阶段并行推断。在本文中，我们提出了针对本地自回归模型的两个并行化方案。我们讨论实施方案的实用性，并提供了与以前的非平行实施相比，压缩运行时获得显着增长的实验证据。
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.
