paper-with-me

홈 › Papers

Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo

2024-03-03 · Jiangbo Pei, Ruizhe Li, Aidong Men, Yang Liu, Xiahai Zhuang, Qingchao Chen

Conventional Multi-Source Free Domain Adaptation (MSFDA) assumes that each source domain provides a single source model, and all source models adopt a uniform architecture. This paper introduces Zoo-MSFDA, a more general setting that allows each source domain to offer a zoo of multiple source models with different architectures. While it enriches the source knowledge, Zoo-MSFDA risks being dominated by suboptimal/harmful models. To address this issue, we theoretically analyze the model selection problem in Zoo-MSFDA, and introduce two principles: transferability principle and diversity principle. Recognizing the challenge of measuring transferability, we subsequently propose a novel Source-Free Unsupervised Transferability Estimation (SUTE). It enables assessing and comparing transferability across multiple source models with different architectures under domain shift, without requiring target labels and source data. Based on above, we introduce a Selection, Ensemble, and Adaptation (SEA) framework to address Zoo-MSFDA, which consists of: 1) source models selection based on the proposed principles and SUTE; 2) ensemble construction based on SUTE-estimated transferability; 3) target-domain adaptation of the ensemble model. Evaluations demonstrate that our SEA framework, with the introduced Zoo-MSFDA setting, significantly improves adaptation performance (e.g., 13.5% on DomainNet). Additionally, our SUTE achieves state-of-the-art performance in transferability estimation.

📄 PDF Abstract BibTeX arXiv:2403.01582

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationModel SelectionSource-Free Domain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation

2024-06-27 · Tao Lian, Jose L. Gómez, Antonio M. López

The last mile of unsupervised domain adaptation (UDA) for semantic segmentation is the challenge of solving the syn-to-real domain gap. Recent UDA methods have progressed significantly, yet they often rely on strategies …

Domain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Ensemble Multi-Source Domain Adaptation with Pseudolabels

2020-09-29 · Seongmin Lee, Hyunsik Jeon, U Kang

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset…

Domain AdaptationEnsemble Learning

Transferable Query Selection for Active Domain Adaptation

2021-06-19 · CVPR 2021 1 · Bo Fu, Zhangjie Cao, Jianmin Wang, Mingsheng Long

Unsupervised domain adaptation (UDA) enables transferring knowledge from a related source domain to a fully unlabeled target domain. Despite the significant advances in UDA, the performance gap remains quite large be…

Active LearningDiversityDomain AdaptationUnsupervised Domain Adaptation

Model Selection, Adaptation, and Combination for Transfer Learning in Wind and Photovoltaic Power Forecasts

2022-04-28 · Jens Schreiber, Bernhard Sick

There is recent interest in using model hubs, a collection of pre-trained models, in computer vision tasks. To utilize the model hub, we first select a source model and then adapt the model for the target to compensate f…

Model SelectionTransfer Learning

Gradual Domain Adaptation via Self-Training of Auxiliary Models

2021-06-18 · Yabin Zhang, Bin Deng, Kui Jia, Lei Zhang

Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, …

Domain AdaptationSemi-supervised Domain Adaptation