GAN
📌 核心贡献
提出生成对抗网络框架：生成器 G 与判别器 D 互相对抗训练，G 学习捕捉数据分布，D 区分真实样本与生成样本。奠定了后续 VQGAN、图像生成等领域的对抗训练基础，至今仍广泛用于 tokenizer 训练中的感知损失与对抗损失。
📖 摘要
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | University of Montreal |
| 发表 | 2014-06-10 |
| 分类 | stat.ML, cs.LG |
| 链接 | arXiv |