مقایسهٔ روشها
روشهای انتخابی خود را کنار هم مرور کنید؛ ردیفهای متفاوت برجسته شدهاند.
| طبقهبندی تصویر خودنظارتی× | تقطیر دانش (Knowledge Distillation)× | |
|---|---|---|
| حوزه | یادگیری عمیق | یادگیری عمیق |
| خانواده | Machine learning | Machine learning |
| سال پیدایش≠ | 2018–2020 | 2015 |
| پدیدآور≠ | Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO) | Hinton, G., Vinyals, O. & Dean, J. |
| نوع≠ | Pretraining + fine-tuning paradigm | Neural network compression (teacher–student) |
| منبع بنیادین≠ | 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 ↗ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ |
| نامهای دیگر | SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation |
| مرتبط≠ | 4 | 5 |
| خلاصه≠ | 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. | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. |
| ScholarGateمجموعهداده ↗ |
|
|