提出域感知模块，让数据压缩更适应多领域图像。
DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
- 用可学习的空间掩码在合成图像中注入域特征。
- 在跨域和跨架构场景下性能显著优于基线方法。
- 无需真实标签，通过频域统计自动识别伪域信息。
数据压缩（DC）是缓解深度学习训练计算与存储负担的有前景方案。然而，现有方法大多忽略现代数据集的多域特性，这些数据集包含来自多个领域的异质图像。本文拓展了DC，提出多域数据压缩（MDDC），旨在压缩适用于单域和多域场景的数据。为此，我们提出域感知模块（DAM），一个训练阶段模块，通过可学习的空间掩码将域相关特征嵌入每个合成图像。由于真实域标签在现实数据集中通常不可用，我们采用基于频率的伪域标签，利用低频幅度统计。DAM仅在压缩过程中激活，因此保持与之前方法相同的每类图像数（IPC）。实验表明，相较于基线数据压缩方法，DAM在域内、域外及跨架构性能上均有持续提升。
原文摘要 · Abstract (English)
Dataset Condensation (DC) has emerged as a promising solution to mitigate the computational and storage burdens associated with training deep learning models. However, existing DC methods largely overlook the multi-domain nature of modern datasets, which are increasingly composed of heterogeneous images spanning multiple domains. In this paper, we extend DC and introduce Multi-Domain Dataset Condensation (MDDC), which aims to condense data that generalizes across both single-domain and multi-domain settings. To this end, we propose the Domain-Aware Module (DAM), a training-time module that embeds domain-related features into each synthetic image via learnable spatial masks. As explicit domain labels are mostly unavailable in real-world datasets, we employ frequency-based pseudo-domain labeling, which leverages low-frequency amplitude statistics. DAM is only active during the condensation process, thus preserving the same images per class (IPC) with prior methods. Experiments show that DAM consistently improves in-domain, out-of-domain, and cross-architecture performance over baseline dataset condensation methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。