Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Samodruhové učení pro detekci objektů× | Samoučení klasifikace obrazu× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2019–2021 | 2018–2020 |
| Tvůrce≠ | He et al. (MoCo); Caron et al. (DINO); Henaff et al. (DetCon) | Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO) |
| Typ≠ | Self-supervised pre-training + supervised fine-tuning | Pretraining + fine-tuning paradigm |
| Původní zdroj≠ | He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9729–9738. DOI ↗ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗ |
| Další názvy | SSL object detection, self-supervised detection, unsupervised pre-training for detection, contrastive pre-training for detection | SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification |
| Příbuzné | 4 | 4 |
| Shrnutí≠ | Self-supervised object detection uses unlabeled image data to pre-train a visual backbone through pretext tasks such as contrastive learning or masked image modeling, then fine-tunes the backbone with a detection head on a smaller labeled dataset. This approach dramatically reduces reliance on expensive bounding-box annotations while matching or approaching fully supervised detection performance. | Self-supervised image classification trains a deep visual encoder on large unlabeled image datasets by solving proxy tasks — such as predicting which two augmented views of the same image are similar — and then fine-tunes only a lightweight classifier head on labeled examples. Pioneered by frameworks such as SimCLR and MoCo around 2020, it drastically reduces the need for expensive manual annotation while achieving accuracy rivaling fully supervised models. |
| ScholarGateDatová sada ↗ |
|
|