视觉-离散Tokenizer01：VQ-VAE（Neural Discrete Representation Learning）

Neural Discrete Representation Learning神经离散表示学习Aaron van den Oord DeepMind avdnoord@google.comOriol Vinyals DeepMind vinyals@google.comKoray Kavukcuoglu DeepMind korayk@google.comAbstract摘要Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector QuantisedVariational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discret