Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seo, Jiwan, Kang, Joonhyuk
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929692824567808
author Seo, Jiwan
Kang, Joonhyuk
author_facet Seo, Jiwan
Kang, Joonhyuk
contents Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive retraining for new bitrates or efficiency requirements. We introduce Rate-Adaptive Quantization (RAQ), a multi-rate codebook adaptation framework for VQ-based generative models. RAQ applies a data-driven approach to generate variable-rate codebooks from a single baseline VQ model, enabling flexible tradeoffs between compression and reconstruction fidelity. Additionally, we provide a simple clustering-based procedure for pre-trained VQ models, offering an alternative when retraining is infeasible. Our experiments show that RAQ performs effectively across multiple rates, often outperforming conventional fixed-rate VQ baselines. By enabling a single system to seamlessly handle diverse bitrate requirements, RAQ extends the adaptability of VQ-based generative models and broadens their applicability to data compression, reconstruction, and generation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14222
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models
Seo, Jiwan
Kang, Joonhyuk
Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive retraining for new bitrates or efficiency requirements. We introduce Rate-Adaptive Quantization (RAQ), a multi-rate codebook adaptation framework for VQ-based generative models. RAQ applies a data-driven approach to generate variable-rate codebooks from a single baseline VQ model, enabling flexible tradeoffs between compression and reconstruction fidelity. Additionally, we provide a simple clustering-based procedure for pre-trained VQ models, offering an alternative when retraining is infeasible. Our experiments show that RAQ performs effectively across multiple rates, often outperforming conventional fixed-rate VQ baselines. By enabling a single system to seamlessly handle diverse bitrate requirements, RAQ extends the adaptability of VQ-based generative models and broadens their applicability to data compression, reconstruction, and generation tasks.
title Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models
topic Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.14222