HierAmp：面向生成式数据集蒸馏的由粗到细自回归语义放大
HierAmp: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
把 VAR 的由粗到细多尺度生成当作层级语义的天然载体，在每个尺度注入类别词元并生成显著性图来引导合成，这个「尺度级条件注入 + 显著性引导」的机制可直接迁移到任何需要分层控制生成内容的视觉合成任务。
原文依据 We leverage the vision autoregressive (VAR) model whose coarse-to-fine generation mirrors this hierarchy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论数据集蒸馏在为原始大规模数据集构建小型替代数据集时，往往优先考虑全局语义接近性。然而，物体语义本身具有层级结构。例如，鸟眼的位置与外观受其头部轮廓的约束。仅靠全局接近性无法刻画不同层级上物体相关结构如何支撑识别。本文研究了层级语义对有效蒸馏数据的贡献。我们利用视觉自回归（VAR）模型——其由粗到细的生成过程恰好对应这种层级结构——并提出 HierAmp，在不同层级上放大语义。在每个 VAR 尺度上，我们注入类别词元，动态识别显著区域，并用其诱导的图引导该尺度上的放大。这仅增加边际推理开销，同时将合成导向判别性部件与结构。实验上，我们发现语义放大在构建粗尺度物体布局时带来更多样的词元选择；相反，在细尺度上，放大使词元使用更集中，增强了对物体相关细节的关注。在多个常用数据集蒸馏基准上，HierAmp 在不显式优化全局接近性的情况下持续提升验证性能，表明语义放大对有效数据集蒸馏的重要性。
英文原文摘要 1415 字符
Dataset distillation often prioritizes global semantic proximity when creating small surrogate datasets for original large-scale ones. However, object semantics are inherently hierarchical. For example, the position and appearance of a bird's eyes are constrained by the outline of its head. Global proximity alone fails to capture how object-relevant structures at different levels support recognition. In this work, we investigate the contributions of hierarchical semantics to effective distilled data. We leverage the vision autoregressive (VAR) model whose coarse-to-fine generation mirrors this hierarchy and propose HierAmp to amplify semantics at different levels. At each VAR scale, we inject class tokens that dynamically identify salient regions and use their induced maps to guide amplification at that scale. This adds only marginal inference cost while steering synthesis toward discriminative parts and structures. Empirically, we find that semantic amplification leads to more diverse token choices in constructing coarse-scale object layouts. Conversely, at fine scales, the amplification concentrates token usage, increasing focus on object-related details. Across popular dataset distillation benchmarks, HierAmp consistently improves validation performance without explicitly optimizing global proximity, demonstrating the importance of semantic amplification for effective dataset distillation.