방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| Variational Autoencoder를 이용한 전이 학습× | 생성적 적대 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2014 (VAE); 2010 (transfer learning survey) | 2014 |
| 창시자≠ | Kingma, D. P. & Welling, M. (VAE); transfer learning framework from Pan & Yang | Goodfellow, I. et al. |
| 유형≠ | Generative model with transferred encoder/decoder | Generative deep learning (adversarial two-network game) |
| 원전≠ | Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR 2014). link ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| 별칭 | TL-VAE, pretrained VAE, VAE transfer learning, fine-tuned variational autoencoder | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| 관련≠ | 6 | 4 |
| 요약≠ | Transfer Learning with a Variational Autoencoder (TL-VAE) reuses an encoder and/or decoder pre-trained on a large source dataset and adapts it to a smaller target domain. By inheriting a rich probabilistic latent space rather than starting from random weights, TL-VAE dramatically reduces the amount of target-domain data needed for high-quality generation or representation learning. | 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 ↗ |
|
|