Report
Few-Shot Learning with Metric-Agnostic Conditional Embeddings
| العنوان: | Few-Shot Learning with Metric-Agnostic Conditional Embeddings |
|---|---|
| المؤلفون: | Hilliard, Nathan, Phillips, Lawrence, Howland, Scott, Yankov, Artëm, Corley, Courtney D., Hodas, Nathan O. |
| سنة النشر: | 2018 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Learning, Statistics - Machine Learning |
| الوصف: | Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison. This allows the network to decide what aspects of each class are important for the comparison at hand. We find that this flexible architecture works well in practice, achieving state-of-the-art performance on the Caltech-UCSD birds fine-grained classification task. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1802.04376 |
| رقم الانضمام: | edsarx.1802.04376 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |