Papers › Domain Generalization using Pretrained Models without Fine-tuning

Domain Generalization using Pretrained Models without Fine-tuning

9 Mar 2022arXiv:2203.04600archive 2025-07-28

Ziyue Li, Kan Ren, Xinyang Jiang, Bo Li, Haipeng Zhang, Dongsheng Li

Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting on source domain and compromise their generalization ability as shown in recent works. Generally, pretrained models possess some level of generalization ability and can achieve decent performance regarding specific domains and samples. However, the generalization performance of pretrained models could vary significantly over different test domains even samples, which raises challenges for us to best leverage pretrained models in DG tasks. In this paper, we propose a novel domain generalization paradigm to better leverage various pretrained models, named specialized ensemble learning for domain generalization (SEDGE). It first trains a linear label space adapter upon fixed pretrained models, which transforms the outputs of the pretrained model to the label space of the target domain. Then, an ensemble network aware of model specialty is proposed to dynamically dispatch proper pretrained models to predict each test sample. Experimental studies on several benchmarks show that SEDGE achieves significant performance improvements comparing to strong baselines including state-of-the-art method in DG tasks and reduces the trainable parameters by ~99% and the training time by ~99.5%.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain GeneralizationEnsemble Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization DomainNet SEDGE+ Average Accuracy 54.7 #16 of 38 Archive leaderboard report
Domain Generalization DomainNet SEDGE Average Accuracy 46.3 #31 of 38 Archive leaderboard report
Domain Generalization Office-Home SEDGE+ Average Accuracy 80.7 #15 of 45 Archive leaderboard report
Domain Generalization Office-Home SEDGE Average Accuracy 79.9 #17 of 45 Archive leaderboard report
Domain Generalization PACS SEDGE+ Average Accuracy 96.1 #12 of 133 Archive leaderboard report
Domain Generalization PACS SEDGE Average Accuracy 84.1 #65 of 133 Archive leaderboard report
Domain Generalization TerraIncognita SEDGE+ Average Accuracy 56.8 #10 of 30 Archive leaderboard report
Domain Generalization TerraIncognita SEDGE Average Accuracy 56.8 #11 of 30 Archive leaderboard report
Domain Generalization VLCS SEDGE+ Average Accuracy 82.2 #13 of 37 Archive leaderboard report
Domain Generalization VLCS SEDGE Average Accuracy 79.8 #21 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AWAREAdapter

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections