방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자기 지도 학습 이미지 분류× | 생성적 적대 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2018–2020 | 2014 |
| 창시자≠ | Chen et al. (SimCLR); He et al. (MoCo); Grill et al. (BYOL); Caron et al. (DINO) | Goodfellow, I. et al. |
| 유형≠ | Pretraining + fine-tuning paradigm | Generative deep learning (adversarial two-network game) |
| 원전≠ | 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 ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| 별칭 | SSL image classification, contrastive visual representation learning, self-supervised visual learning, unsupervised pretraining for image classification | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| 관련 | 4 | 4 |
| 요약≠ | 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. | A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation. |
| ScholarGate데이터셋 ↗ |
|
|