تقرير
In Search for a Generalizable Method for Source Free Domain Adaptation
العنوان: | In Search for a Generalizable Method for Source Free Domain Adaptation |
---|---|
المؤلفون: | Boudiaf, Malik, Denton, Tom, van Merriënboer, Bart, Dumoulin, Vincent, Triantafillou, Eleni |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning |
الوصف: | Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data. In this work, we apply existing SFDA techniques to a challenging set of naturally-occurring distribution shifts in bioacoustics, which are very different from the ones commonly studied in computer vision. We find existing methods perform differently relative to each other than observed in vision benchmarks, and sometimes perform worse than no adaptation at all. We propose a new simple method which outperforms the existing methods on our new shifts while exhibiting strong performance on a range of vision datasets. Our findings suggest that existing SFDA methods are not as generalizable as previously thought and that considering diverse modalities can be a useful avenue for designing more robust models. Comment: ICML 2023 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2302.06658 |
رقم الأكسشن: | edsarx.2302.06658 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |