Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Vāji uzraudzīta konvolucionālā neironu tīkls× | Daļēji uzraudzīts konvolucionāls neironu tīkls× | |
|---|---|---|
| Nozare | Dziļā mācīšanās | Dziļā mācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2015–2016 | 2013–2017 |
| Autors≠ | Oquab, M. et al.; Zhou, B. et al. | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) |
| Tips≠ | Weakly supervised deep learning | Semi-supervised deep learning |
| Pirmavots≠ | Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929. 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 ↗ |
| Citi nosaukumi | WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN |
| Saistītās | 5 | 5 |
| Kopsavilkums≠ | A weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals. | 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. |
| ScholarGateDatu kopa ↗ |
|
|