UniComp：从信息唯一性重新审视视频压缩
UniComp: Rethinking Video Compression Through Informational Uniqueness
用条件熵与「信息唯一性」度量词元冗余，可在任意视觉 Transformer 的视频/图像词元压缩中替换启发式重要性打分，为下游视频模型提供可复用的自适应词元分配策略。
原文依据 we formulate the vision compression as an optimization problem that minimizes conditional entropy (reconstruction error) between retained and full tokens
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论与基于注意力的压缩方法不同，本文提出一种由信息唯一性驱动的视频压缩框架 UniComp，旨在有限计算预算下最大化视频表示的信息保真度。我们从信息论视角出发，将视觉压缩建模为一个优化问题，即最小化保留词元与完整词元之间的条件熵（重建误差）。为此，我们引入信息唯一性这一概念，用以度量词元之间的内在冗余，并将其与重建误差建立联系。基于唯一性，我们设计了三个模块——帧组融合、词元分配与空间动态压缩——分别渐进地执行语义帧分组、自适应资源分配与细粒度空间压缩。大量实验表明，在有限计算预算下，UniComp 在保留关键视觉词元方面持续优于现有压缩方法，凸显了信息唯一性在词元压缩有效性中的关键作用。
英文原文摘要 1117 字符
Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained computational budgets. Starting from the information-theoretic perspective, we formulate the vision compression as an optimization problem that minimizes conditional entropy (reconstruction error) between retained and full tokens. To achieve this, we introduce the notion of information uniqueness to measure intrinsic redundancy among tokens to link with reconstruction error. Based on uniqueness, we design three modules--Frame Group Fusion, Token Allocation, and Spatial Dynamic Compression--that progressively perform semantic frame grouping, adaptive resource allocation, and fine-grained spatial compression. Extensive experiments demonstrate that UniComp consistently outperforms existing compression methods in preserving essential visual tokens under limited computational budgets, highlighting the pivotal role of information uniqueness in token compression efficacy.