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。
| 弱监督图像分类× | 微调图像分类× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2014–2016 | 2010–2014 |
| 提出者≠ | Multiple contributors; class activation map approach: Zhou et al. | Yosinski, J. et al.; Pan, S. J. & Yang, Q. |
| 类型≠ | Weakly supervised deep learning paradigm | Transfer learning / fine-tuning |
| 开创性文献≠ | Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929. DOI ↗ | 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 ↗ |
| 别名 | WSL image classification, image-level supervised classification, noisy-label image classification, weakly labeled visual recognition | fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier |
| 相关 | 5 | 5 |
| 摘要≠ | Weakly supervised image classification trains convolutional or transformer-based networks using only coarse, incomplete, or noisy supervision — such as image-level category labels, hashtags, or web-scraped tags — without requiring precise bounding boxes or pixel annotations. This dramatically reduces labeling cost while still enabling high-accuracy visual recognition at scale. | 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. |
| ScholarGate数据集 ↗ |
|
|