Online clustered codebook

Vector Quantisation (VQ) is experiencing a comeback in machine learning, where it is increasingly used in representation learning. However, optimizing the codevectors in existing VQ-VAE is not entirely trivial. A problem is codebook collapse, where only a small subset of codevectors receive gradient...

Full description

Bibliographic Details
Main Authors: Zheng, C, Vedaldi, A
Format: Internet publication
Language:English
Published: 2023