DAM: Domain-Aware Module for Multi-Domain Dataset Condensation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Choi, Jaehyun, Han, Gyojin, Lee, Dong-Jae, Baek, Sunghyun, Kim, Junmo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912400091906048
author Choi, Jaehyun
Han, Gyojin
Lee, Dong-Jae
Baek, Sunghyun
Kim, Junmo
author_facet Choi, Jaehyun
Han, Gyojin
Lee, Dong-Jae
Baek, Sunghyun
Kim, Junmo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
Choi, Jaehyun
Han, Gyojin
Lee, Dong-Jae
Baek, Sunghyun
Kim, Junmo
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.22387