用专家混合模型提升图像压缩效率，比VVC快近17%。
Mixture-of-Experts-based Entropy Model for Learned Image Compression
- 采用专家混合机制，仅激活输入图像所需的参数子集。
- 在Kodak数据集上，相比VVC实现16.85%的率失真增益。
- 适合追求高效图像压缩的工程师和研究者。
近年来，端到端学习的图像压缩模型取得了显著进展，其压缩效率已超越现有传统方法。最近，专家混合（Mixture of Experts, MoE）方法在自然语言处理与计算机视觉任务中表现出色。本文首次将MoE引入学习型图像压缩领域，提出基于专家混合的熵模型（MoEE），使模型能根据输入图像动态选择性激活所需参数子集。实验表明，该模型在Kodak数据集上相较VVC标准实现了-16.85%的BD-Rate改善，显著提升了压缩性能。
原文摘要 · Abstract (English)
Learned image compression has seen significant progress in recent years with the development of end-to-end learned models that achieve better compression efficiency than state-of-the-art conventional methods. Recently, Mixture of Experts (MoE) approaches have seen promising results in NLP and computer vision tasks. In this paper, we introduce the MoE approach to learned image compression. We propose a MoE-based Entropy model (MoEE) for learned image compression, allowing the model to selectively activate only the subset of parameters required for the input image. Our model achieves a BD-Rate improvement over VVC of -16.85% on the Kodak dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。