方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 微调图像分类× | 微调卷积神经网络× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2010–2014 | 2012–2014 |
| 提出者≠ | Yosinski, J. et al.; Pan, S. J. & Yang, Q. | Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward |
| 类型≠ | Transfer learning / fine-tuning | Transfer learning technique (supervised fine-tuning) |
| 开创性文献≠ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link ↗ | 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 ↗ |
| 别名 | fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier | Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network |
| 相关 | 5 | 5 |
| 摘要≠ | Fine-tuned image classification adapts a large neural network pretrained on a broad image corpus (such as ImageNet) to a specific target domain by continuing training on labeled domain images. This approach achieves strong accuracy with far fewer target-domain samples than training from scratch, making it the dominant paradigm for applied computer vision tasks. | 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. |
| ScholarGate数据集 ↗ |
|
|