固定锚点不足够：面向数据集蒸馏的动态检索与持续同调
Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation
提出动态检索连接与持续拓扑对齐，可复用于其他需要匹配教师特征分布的数据集蒸馏或合成数据生成任务，以提升类内多样性和泛化性。
原文依据 Dynamic Retrieval Connection (DRC) selects a real patch from a prebuilt pool by minimizing a fit-complexity score in teacher feature space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论解耦数据集蒸馏（DD）通过匹配冻结教师的统计量将大规模语料压缩为少量合成图像。然而，当前残差匹配流程依赖静态真实图像块，造成拟合复杂度差距和拉向锚点效应，降低类内多样性并损害泛化性。为解决这些问题，我们提出RETA——一种用于解耦DD的检索与拓扑对齐框架。首先，动态检索连接（DRC）通过在教师特征空间中最小化拟合复杂度得分，从预构建池中选择真实图像块；所选图像块通过残差连接注入，以收紧特征拟合同时控制注入复杂度。其次，持续拓扑对齐（PTA）利用持续同调正则化合成过程：我们构建互k近邻特征图，计算分量和环的持续图像，并惩罚真实集与合成集之间的拓扑差异，从而缓解拉向锚点效应。在CIFAR-100、Tiny-ImageNet、ImageNet-1K及多个ImageNet子集上，RETA在相当的时间和内存下持续优于多种基线，尤其在ImageNet-1K上使用ResNet-18、每类50张图像时达到64.3%的top-1准确率，比最佳先前方法提升3.1%。
英文原文摘要 1259 字符
Decoupled dataset distillation (DD) compresses large corpora into a few synthetic images by matching a frozen teacher's statistics. However, current residual-matching pipelines rely on static real patches, creating a fit-complexity gap and a pull-to-anchor effect that reduce intra-class diversity and hurt generalization. To address these issues, we introduce RETA--a Retrieval and Topology Alignment framework for decoupled DD. First, Dynamic Retrieval Connection (DRC) selects a real patch from a prebuilt pool by minimizing a fit-complexity score in teacher feature space; the chosen patch is injected via a residual connection to tighten feature fit while controlling injected complexity. Second, Persistent Topology Alignment (PTA) regularizes synthesis with persistent homology: we build a mutual k-NN feature graph, compute persistence images of components and loops, and penalize topology discrepancies between real and synthetic sets, mitigating pull-to-anchor effect. Across CIFAR-100, Tiny-ImageNet, ImageNet-1K, and multiple ImageNet subsets, RETA consistently outperforms various baselines under comparable time and memory, especially reaching 64.3% top-1 accuracy on ImageNet-1K with ResNet-18 at 50 images per class, +3.1% over the best prior.