DeCO：用于细粒度数据集蒸馏的判别证据组合

中文摘要 AI 辅助

数据集蒸馏将大型训练集压缩为紧凑的合成集，同时保留其下游效用。然而，现有方法主要保留全局图像统计，可能忽略细粒度视觉分类（FGVC）所需的局部证据，如物体部件、细微纹理和特定区域结构。我们将细粒度数据集蒸馏形式化为受限预算下的判别证据保留问题，提出判别证据组合（DeCO）方法。DeCO利用预训练TransFG教师模型的注意力回滚识别信息性图像块，应用空间多样化减少冗余覆盖，将所得区域组织为按类别划分的证据库；随后将多个同类区域打包为紧凑的网格组合图像。教师模型仅用于数据集构建，下游学生模型采用标准硬标签监督训练，无需教师logits。在CUB-200-2011、FGVC-Aircraft和Stanford Cars数据集上的实验表明，DeCO在不同IPC预算下始终优于代表性的核心集和数据集蒸馏基线方法。

英文摘要

Dataset distillation compresses a large training set into a compact synthetic set while preserving its downstream utility. However, existing methods primarily preserve global image statistics and may overlook the localized evidence essential for fine-grained visual classification (FGVC), such as object parts, subtle textures, and region-specific structures. We formulate fine-grained dataset distillation as budgeted discriminative-evidence preservation and propose Discriminative Evidence Composition (DeCO). DeCO uses attention rollout from a pretrained TransFG teacher to identify informative patches, applies spatial diversification to reduce redundant coverage, and organizes the resulting regions into class-wise evidence banks. Multiple same-class regions are then packed into compact grid-composed images. The teacher is used only for dataset construction, whereas downstream students are trained with standard hard-label supervision without teacher logits. Experiments on CUB-200-2011, FGVC-Aircraft, and Stanford Cars show that DeCO consistently outperforms representative coreset and dataset-distillation baselines under different IPC budgets.

发表机构

• University of Science and Technology of China（中国科学技术大学）
• Hokkaido University（北海道大学）
• The University of Queensland（昆士兰大学）
• Shanghai AI Laboratory（上海人工智能实验室）
• Dalian University of Technology（大连理工大学）

机构由 AI 辅助整理，请以论文原文为准。