Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917860174987264 |
|---|---|
| author | Lee, Gyuseong Jang, Wooseok Kim, Jinhyeon Jung, Jaewoo Kim, Seungryong |
| author_facet | Lee, Gyuseong Jang, Wooseok Kim, Jinhyeon Jung, Jaewoo Kim, Seungryong |
| contents | Learning robust vision models that perform well in out-of-distribution (OOD) situations is an important task for model deployment in real-world settings. Despite extensive research in this field, many proposed methods have only shown minor performance improvements compared to the simplest empirical risk minimization (ERM) approach, which was evaluated on a benchmark with a limited hyperparameter search space. Our focus in this study is on leveraging the knowledge of large pretrained models to improve handling of OOD scenarios and tackle domain generalization problems. However, prior research has revealed that naively fine-tuning a large pretrained model can impair OOD robustness. Thus, we employ parameter-efficient fine-tuning (PEFT) techniques to effectively preserve OOD robustness while working with large models. Our extensive experiments and analysis confirm that the most effective approaches involve ensembling diverse models and increasing the scale of pretraining. As a result, we achieve state-of-the-art performance in domain generalization tasks. Our code and project page are available at: https://cvlab-kaist.github.io/MoA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_11031 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters Lee, Gyuseong Jang, Wooseok Kim, Jinhyeon Jung, Jaewoo Kim, Seungryong Computer Vision and Pattern Recognition Learning robust vision models that perform well in out-of-distribution (OOD) situations is an important task for model deployment in real-world settings. Despite extensive research in this field, many proposed methods have only shown minor performance improvements compared to the simplest empirical risk minimization (ERM) approach, which was evaluated on a benchmark with a limited hyperparameter search space. Our focus in this study is on leveraging the knowledge of large pretrained models to improve handling of OOD scenarios and tackle domain generalization problems. However, prior research has revealed that naively fine-tuning a large pretrained model can impair OOD robustness. Thus, we employ parameter-efficient fine-tuning (PEFT) techniques to effectively preserve OOD robustness while working with large models. Our extensive experiments and analysis confirm that the most effective approaches involve ensembling diverse models and increasing the scale of pretraining. As a result, we achieve state-of-the-art performance in domain generalization tasks. Our code and project page are available at: https://cvlab-kaist.github.io/MoA |
| title | Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.11031 |