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。
| 自己教師あり能動学習× | 転移学習× | |
|---|---|---|
| 分野 | 機械学習 | 機械学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 2020–2021 | 2010 (formalized); 1990s (early roots) |
| 提唱者≠ | Bengar et al. and concurrent works (multiple groups) | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) |
| 種類≠ | Hybrid active-learning and self-supervised pre-training framework | Learning paradigm |
| 原典≠ | Bengar, J. Z., van de Weijer, J., Twardowski, B., & Raducanu, B. (2021). Reducing Label Effort: Self-Supervised Meets Active Learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1631–1639. link ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| 別名 | SSL-AL, self-supervised active learning, semi-supervised active learning with self-supervision, label-efficient self-supervised learning | TL, domain adaptation, fine-tuning, pre-trained model adaptation |
| 関連≠ | 5 | 3 |
| 概要≠ | Self-supervised Active Learning (SSL-AL) is a label-efficient machine-learning paradigm that pre-trains a model on unlabeled data using self-supervised objectives, then strategically queries a human oracle for the most informative labels using an active-learning acquisition function. The result is strong predictive performance with a fraction of the annotation cost required by fully supervised approaches. | 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. |
| ScholarGateデータセット ↗ |
|
|