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

• URL: http://arxiv.org/abs/2505.22387v1
• Date: Wed, 28 May 2025 14:13:38 GMT
• Title: DAM: Domain-Aware Module for Multi-Domain Dataset Condensation
• Authors: Jaehyun Choi, Gyojin Han, Dong-Jae Lee, Sunghyun Baek, Junmo Kim,
• Abstract summary: Multi-Domain dataset Condensation (MDDC) aims to condense data that generalizes across both single-domain and multi-domain settings.<n> Domain-Aware Module (DAM) embeds domain-related features into each synthetic image via learnable spatial masks.<n>DAM consistently improves in-domain, out-of-domain, and cross-architecture performance over baseline dataset condensation methods.
• Score: 25.14130854166058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting [67.38137379297717]
  Multidomain crowd counting aims to learn a general model for multiple diverse datasets. Deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. We propose a Modulating Domain-specific Knowledge Network (MDKNet) to handle the domain bias issue in multidomain crowd counting.
  arXiv  Detail & Related papers  (2024-02-06T06:49:04Z)
• Adapting Self-Supervised Representations to Multi-Domain Setups [47.03992469282679]
  Current state-of-the-art self-supervised approaches, are effective when trained on individual domains but show limited generalization on unseen domains. We propose a general-purpose, lightweight Domain Disentanglement Module that can be plugged into any self-supervised encoder.
  arXiv  Detail & Related papers  (2023-09-07T20:05:39Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• Modular Domain Adaptation for Conformer-Based Streaming ASR [28.398302172150636]
  We propose a framework that enables a single model to process multidomain data while keeping all parameters domain-specific. On a streaming Conformer transducer trained only on video caption data, experimental results show that an MDA-based model can reach similar performance as the multidomain model on other domains.
  arXiv  Detail & Related papers  (2023-05-22T18:49:35Z)
• Dynamic Instance Domain Adaptation [109.53575039217094]
  Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels. We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance. Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
  arXiv  Detail & Related papers  (2022-03-09T20:05:54Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• Unsupervised Multi-Source Domain Adaptation for Person Re-Identification [39.817734080890695]
  Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data. We introduce the multi-source concept into UDA person re-ID field, where multiple source datasets are used during training. The proposed method outperforms state-of-the-art UDA person re-ID methods by a large margin, and even achieves comparable performance to the supervised approaches without any post-processing techniques.
  arXiv  Detail & Related papers  (2021-04-27T03:33:35Z)
• Achieving Domain Generalization in Underwater Object Detection by Image Stylization and Domain Mixup [8.983901488753967]
  Existing underwater object detection methods degrade seriously when facing domain shift problem caused by complicated underwater environments. We propose a domain generalization method from the aspect of data augmentation. Comprehensive experiments on S-UODAC 2020 datasets demonstrate that the proposed method is able to learn domain-invariant representations.
  arXiv  Detail & Related papers  (2021-04-06T01:45:07Z)
• Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [102.42638795864178]
  We propose a principled meta-learning based approach to OCDA for semantic segmentation. We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
  arXiv  Detail & Related papers  (2020-12-15T13:21:54Z)
• Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
  Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
  arXiv  Detail & Related papers  (2020-11-25T12:02:57Z)
• Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder [5.933303832684138]
  We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data.
  arXiv  Detail & Related papers  (2020-03-15T19:55:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.