Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Pooltreenitav semantiline segmentatsioon× | Pooltreenimisega konvolutsiooniline närvivõrk× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2018–2020 | 2013–2017 |
| Looja≠ | Multiple (Ouali et al., Zou et al., Chen et al.) | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) |
| Tüüp≠ | Semi-supervised deep learning for pixel-level classification | Semi-supervised deep learning |
| Algallikas≠ | Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-Supervised Semantic Segmentation with Cross-Consistency Training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12674–12684. DOI ↗ | Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning. link ↗ |
| Rööpnimetused | Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN |
| Seotud | 5 | 5 |
| Kokkuvõte≠ | Semi-supervised semantic segmentation trains pixel-level labeling models using a small set of fully labeled images combined with a much larger set of unlabeled images. Techniques such as pseudo-labeling and consistency regularization extract supervisory signal from unlabeled data, making it possible to achieve near-fully-supervised accuracy at a fraction of the annotation cost. | A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort. |
| ScholarGateAndmestik ↗ |
|
|