Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Трансферне навчання з детекцією об'єктів× | Трансферне навчання для класифікації зображень× | |
|---|---|---|
| Галузь | Глибоке навчання | Глибоке навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2010–2014 | 2010–2012 |
| Автор методу≠ | Girshick, R. et al. (R-CNN line); Pan & Yang (transfer learning framework) | Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone) |
| Тип≠ | Transfer learning / fine-tuning | Transfer learning / supervised classification |
| Основоположне джерело | Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| Інші назви | pretrained object detector, fine-tuned object detection, TL-OD, domain-adapted object detection | pretrained CNN image classification, fine-tuned image classifier, domain-adapted image classifier, TL-IC |
| Пов'язані≠ | 3 | 4 |
| Підсумок≠ | Transfer learning with object detection starts from a deep neural network pretrained on a large image dataset — typically ImageNet for the backbone or COCO for the full detector — and adapts it to detect objects in a new domain. By reusing learned visual representations, it achieves strong detection accuracy with far fewer annotated images than training from scratch would require. | Transfer Learning with Image Classification reuses a deep neural network backbone — typically a CNN or Vision Transformer — pretrained on a large dataset such as ImageNet, and adapts it to classify images in a new target domain. By inheriting general visual features from the source task, the approach achieves high accuracy with far fewer labeled images than training from scratch. |
| ScholarGateНабір даних ↗ |
|
|