MoECodec: 通过混合专家实现面向人机联合感知的图像压缩
MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts
AI总结：
提出MoECodec，一种基于混合专家（MoE）的令牌感知图像压缩框架，通过令牌级动态计算和稳定路由策略，在单一模型中同时支持多个下游机器视觉任务，并在图像重建和机器任务上均取得一致提升。
摘要：
面向机器的图像压缩需要一种统一的编解码器，以服务于多个下游视觉任务。现有方法要么采用任务特定的端到端设计，导致参数和部署开销增加，要么依赖于基于迁移的适应方法，这些方法仍然是外部附加的且任务设计具有启发性。这两类工作的一个关键限制是它们很大程度上采用静态计算模式，即对不同的令牌应用相似的变换，尽管不同图像区域对于机器感知具有显著不同的语义重要性和复杂度。我们提出了MoECodec，一种令牌感知的图像压缩框架，在单一模型中支持多个下游任务。MoECodec用令牌级混合专家（MoE）替换基于Transformer的压缩模型中的FFN层，实现了根据输入内容和任务目标动态调整的令牌级计算。为了使MoE在压缩模型中有效，我们引入了一种稳定的路由策略，该策略结合了专家选择路由和空间总变分正则化，以鼓励空间上一致的分配，并提出了一个轻量级的专家架构——组洗牌MLP（GShMLP），以控制参数增长。大量实验表明，在传统图像重建和机器任务上，我们的方法均比基线方法有一致的提升。
英文摘要：
Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific end-to-end designs, raising parameter and deployment overhead, or rely on transfer-based adaptations that remain externally attached and heuristic task design. A key limitation shared by both lines of work is their largely static computation pattern, which applies similar transformations across tokens despite the fact that different image regions exhibit markedly different semantic importance and complexity for machine perception. We propose MoECodec, a token-aware image compression framework that supports multiple downstream tasks within a single model. MoECodec replaces the FFN layers in transformer-based compression model token-wise Mixture-of-Experts (MoE), enabling dynamic, token-level computation conditioned on the input content and task objective. To make MoE effective in compression model, we introduce a stable routing strategy that combines expert-choice routing with spatial total variation regularization to encourage spatially coherent assignments, and we propose a lightweight expert architecture, Group Shuffle MLP (GShMLP), to control parameter growth. Extensive experiments show consistent improvement against baselines on both conventional image reconstruction and machine tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
