Authors
- Yuhta Takida
- Takashi Shibuya
- Wei-Hsiang Liao
- Chieh-Hsin Lai
- Junki Ohmura*
- Toshimitsu Uesaka
- Naoki Murata
- Shusuke Takahashi*
- Toshiyuki Kumakura*
- Yuki Mitsufuji
* External authors
Venue
- ICML 2022
Date
- 2022
Share
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
Junki Ohmura*
Shusuke Takahashi*
Toshiyuki Kumakura*
* External authors
ICML 2022
2022
Abstract
One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training scheme of VQ-VAE, which involves some carefully designed heuristics, underlies this issue. In this paper, we propose a new training scheme that extends the standard VAE via novel stochastic dequantization and quantization, called stochastically quantized variational autoencoder (SQ-VAE). In SQ-VAE, we observe a trend that the quantization is stochastic at the initial stage of the training but gradually converges toward a deterministic quantization, which we call self-annealing. Our experiments show that SQ-VAE improves codebook utilization without using common heuristics. Furthermore, we empirically show that SQ-VAE is superior to VAE and VQ-VAE in vision- and speech-related tasks.
Related Publications
Consistency Training (CT) has recently emerged as a promising alternative to diffusion models, achieving competitive performance in image generation tasks. However, non-distillation consistency training often suffers from high variance and instability, and analyzing and impr…
Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match musical versions at the track level (e.g., whole song). However, most applications require to …
Diffusion models have demonstrated exceptional performances in various fields of generative modeling, but suffer from slow sampling speed due to their iterative nature. While this issue is being addressed in continuous domains, discrete diffusion models face unique challenge…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
