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。
| 畳み込みニューラルネットワークを用いた転移学習× | セマンティックセグメンテーション× | |
|---|---|---|
| 分野 | 深層学習 | 深層学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 2010–2014 | 2015 |
| 提唱者≠ | Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al. | Long, J., Shelhamer, E., & Darrell, T. |
| 種類≠ | Transfer learning applied to convolutional neural networks | Dense prediction / pixel-wise classification |
| 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 ↗ | Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440. DOI ↗ |
| 別名 | TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN | pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation |
| 関連≠ | 4 | 5 |
| 概要≠ | Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch. | Semantic segmentation assigns a class label to every pixel in an image, producing a dense, category-annotated map of the scene. Unlike object detection, which draws bounding boxes, it delineates the exact spatial extent of each class, making it indispensable in medical imaging, autonomous driving, satellite analysis, and any task where precise region boundaries matter. |
| ScholarGateデータセット ↗ |
|
|