This paper presents a novel sampling scheme for masked non-autoregressive
generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and
Token-Critic in their sampling processes, and propose Enhanced Sampling Scheme
(ESS) to overcome these limitations. ESS explicitly ensures both sample
diversity and fidelity, and consists of three stages: Naive Iterative Decoding,
Critical Reverse Sampling, and Critical Resampling. ESS starts by sampling a
token set using the naive iterative decoding as proposed in MaskGIT, ensuring
sample diversity. Then, the token set undergoes the critical reverse sampling,
masking tokens leading to unrealistic samples. After that, critical resampling
reconstructs masked tokens until the final sampling step is reached to ensure
high fidelity. Critical resampling uses confidence scores obtained from a
self-Token-Critic to better measure the realism of sampled tokens, while
critical reverse sampling uses the structure of the quantized latent vector
space to discover unrealistic sample paths. We demonstrate significant
performance gains of ESS in both unconditional sampling and class-conditional
sampling using all the 128 datasets in the UCR Time Series archive.

该论文提出了一种用于掩码非自回归生成建模的新型采样方案，该方案通过解决 TimeVQVAE、MaskGIT 和 Token-Critic 在采样过程中的局限性，显式保证采样的多样性和真实性，并由三个阶段组成：Naive Iterative Decoding、Critical Reverse Sampling 和 Critical Resampling。通过在 UCR 时间序列存档中使用所有 128 个数据集，在无条件采样和类条件采样方面，我们展示了 ESS 的显著性能提升。