Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Svakt overvåket konvolusjonelt nevralt nettverk× | Finetunet konvolusjonelt nevralt nettverk× | |
|---|---|---|
| Fagfelt | Dyp læring | Dyp læring |
| Familie | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2015–2016 | 2012–2014 |
| Opphavsperson≠ | Oquab, M. et al.; Zhou, B. et al. | Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward |
| Type≠ | Weakly supervised deep learning | Transfer learning technique (supervised fine-tuning) |
| Opprinnelig kilde≠ | 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 ↗ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27. link ↗ |
| Alias | WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels | Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network |
| Relaterte | 5 | 5 |
| Sammendrag≠ | 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. | Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch. |
| ScholarGateDatasett ↗ |
|
|