방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 객체 탐지를 위한 전이 학습× | 미세 조정된 합성곱 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2010–2014 | 2012–2014 |
| 창시자≠ | Girshick, R. et al. (R-CNN line); Pan & Yang (transfer learning framework) | Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward |
| 유형≠ | Transfer learning / fine-tuning | Transfer learning technique (supervised fine-tuning) |
| 원전≠ | Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27. link ↗ |
| 별칭 | pretrained object detector, fine-tuned object detection, TL-OD, domain-adapted object detection | Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network |
| 관련≠ | 3 | 5 |
| 요약≠ | 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. | Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch. |
| ScholarGate데이터셋 ↗ |
|
|