UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912041463185408 |
|---|---|
| author | Kalluri, Tarun Ravichandran, Sreyas Chandraker, Manmohan |
| author_facet | Kalluri, Tarun Ravichandran, Sreyas Chandraker, Manmohan |
| contents | In this work, we take a deeper look into the diverse factors that influence the efficacy of modern unsupervised domain adaptation (UDA) methods using a large-scale, controlled empirical study. To facilitate our analysis, we first develop UDA-Bench, a novel PyTorch framework that standardizes training and evaluation for domain adaptation enabling fair comparisons across several UDA methods. Using UDA-Bench, our comprehensive empirical study into the impact of backbone architectures, unlabeled data quantity, and pre-training datasets reveals that: (i) the benefits of adaptation methods diminish with advanced backbones, (ii) current methods underutilize unlabeled data, and (iii) pre-training data significantly affects downstream adaptation in both supervised and self-supervised settings. In the context of unsupervised adaptation, these observations uncover several novel and surprising properties, while scientifically validating several others that were often considered empirical heuristics or practitioner intuitions in the absence of a standardized training and evaluation framework. The UDA-Bench framework and trained models are publicly available at https://github.com/ViLab-UCSD/UDABench_ECCV2024. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15264 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework Kalluri, Tarun Ravichandran, Sreyas Chandraker, Manmohan Machine Learning Computer Vision and Pattern Recognition In this work, we take a deeper look into the diverse factors that influence the efficacy of modern unsupervised domain adaptation (UDA) methods using a large-scale, controlled empirical study. To facilitate our analysis, we first develop UDA-Bench, a novel PyTorch framework that standardizes training and evaluation for domain adaptation enabling fair comparisons across several UDA methods. Using UDA-Bench, our comprehensive empirical study into the impact of backbone architectures, unlabeled data quantity, and pre-training datasets reveals that: (i) the benefits of adaptation methods diminish with advanced backbones, (ii) current methods underutilize unlabeled data, and (iii) pre-training data significantly affects downstream adaptation in both supervised and self-supervised settings. In the context of unsupervised adaptation, these observations uncover several novel and surprising properties, while scientifically validating several others that were often considered empirical heuristics or practitioner intuitions in the absence of a standardized training and evaluation framework. The UDA-Bench framework and trained models are publicly available at https://github.com/ViLab-UCSD/UDABench_ECCV2024. |
| title | UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.15264 |