Masked Vector Quantization

arXiv:2301.06626v2 Announce Type: replace
Abstract: Generative models with discrete latent representations have recently demonstrated an impressive ability to learn complex high-dimensional data distributions. However, their performance relies on a long sequence of tokens per instance and a large number of codebook entries, resulting in long sampling times and considerable computation to fit the categorical posterior. To address these issues, we propose the Masked Vector Quantization (MVQ) framework which increases the representational capacity of each code vector by learning mask configurations …

abstract arxiv categorical computation cs.cv cs.lg data generative generative models however instance learn per performance posterior quantization sampling tokens type vector