Attentive VQ-VAE

TL;DR

This paper introduces Attentive VQ-VAE, which enhances traditional VQ-VAE models with a Residual Encoder and Pixel Attention, improving data representation and generation capabilities efficiently.

Contribution

The paper proposes the Attentive Residual Encoder (AREN) with inter-pixel auto-attention for better VQ-VAE performance while maintaining practical parameter levels.

Findings

Significant improvements in data representation quality.

Enhanced generative performance across tasks.

Efficient attention mechanism with minimal parameters.

Abstract

We present a novel approach to enhance the capabilities of VQ-VAE models through the integration of a Residual Encoder and a Residual Pixel Attention layer, named Attentive Residual Encoder (AREN). The objective of our research is to improve the performance of VQ-VAE while maintaining practical parameter levels. The AREN encoder is designed to operate effectively at multiple levels, accommodating diverse architectural complexities. The key innovation is the integration of an inter-pixel auto-attention mechanism into the AREN encoder. This approach allows us to efficiently capture and utilize contextual information across latent vectors. Additionally, our models uses additional encoding levels to further enhance the model's representational power. Our attention layer employs a minimal parameter approach, ensuring that latent vectors are modified only when pertinent information from other pixels is available. Experimental results demonstrate that our proposed modifications lead to significant improvements in data representation and generation, making VQ-VAEs even more suitable for a wide range of applications as the presented.