方法对比

	自编码器	扩散模型	生成对抗网络
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2006	2020	2014
提出者	Hinton, G.E. & Salakhutdinov, R.R.	Ho, J., Jain, A. & Abbeel, P.	Goodfellow, I. et al.
类型	Neural network (encoder-decoder)	Generative deep learning (denoising diffusion)	Generative deep learning (adversarial two-network game)
开创性文献	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
别名	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
相关	4	4	4
摘要	An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.	A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.	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.