مقایسهٔ روشها
روشهای انتخابی خود را کنار هم مرور کنید؛ ردیفهای متفاوت برجسته شدهاند.
| طبقهبندی تصویر نیمهنظارتشده× | طبقهبندی تصویر با تنظیم دقیق (Fine-Tuned Image Classification)× | |
|---|---|---|
| حوزه | یادگیری عمیق | یادگیری عمیق |
| خانواده | Machine learning | Machine learning |
| سال پیدایش≠ | 2013–2020 | 2010–2014 |
| پدیدآور≠ | Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch) | Yosinski, J. et al.; Pan, S. J. & Yang, Q. |
| نوع≠ | Semi-supervised deep learning | Transfer learning / fine-tuning |
| منبع بنیادین≠ | Lee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning. link ↗ | 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 ↗ |
| نامهای دیگر | SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification | fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier |
| مرتبط | 5 | 5 |
| خلاصه≠ | Semi-supervised image classification trains deep neural networks on a small set of labeled images together with a much larger pool of unlabeled images. Techniques such as pseudo-labeling, consistency regularization, and confidence thresholding allow the model to leverage the structure of unlabeled data, dramatically reducing the need for expensive manual annotation while approaching fully-supervised accuracy. | 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. |
| ScholarGateمجموعهداده ↗ |
|
|