手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| 転移学習× | ビジョントランスフォーマー× | |
|---|---|---|
| 分野≠ | 機械学習 | 深層学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 2010 (formalized); 1990s (early roots) | 2021 |
| 提唱者≠ | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) | Dosovitskiy, A. et al. |
| 種類≠ | Learning paradigm | Transformer architecture for images (self-attention over patches) |
| 原典≠ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| 別名 | TL, domain adaptation, fine-tuning, pre-trained model adaptation | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| 関連≠ | 3 | 5 |
| 概要≠ | Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGateデータセット ↗ |
|
|