.png){kind=icon}
返回
Optimizing codebook training through control chart analysis
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01555-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Frequent use of codebook resets to enhance the usage of the Vector Quantization Variational Autoencoder (VQ-VAE) may significantly alter the codebook distribution and consequently diminish the training efficiency. In this work, we introduce a novel codebook learning approach called Exponentially Weighted Moving Average Control VQ-VAE (ECVQ-VAE). This method considers the nearest neighbor distance of the codebook during training as a monitoring sample and constructs a control line. Our quantizer restricts the update process of codebook vectors based on whether the drift during monitoring exceeds the control line while simultaneously adjusting the overall usage distribution of the codebook by promoting competition. This process enables an optimization that sustains full codebook usage while reducing the training demands. We demonstrate that our approach achieves better results than the existing methods in lightweight scenarios and extensively validate the generalizability of our quantizer across various datasets, tasks, and architectures (VQ-VAE, VQ-GAN).
Keyword:
Codebook learning
Control chart
Vector quantization
Statistical process control
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
Multi2Human: Controllable human image generation with multimodal controlsMulti2Human: 具有多模式控件的可控人体图像生成.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Supramolecular Approaches for Taming the Chemo- and Regiochemistry of C60 Addition Reactions驯服C60加成反应的化学和区域化学的超分子方法
OAAI
OAAI分享收藏分享收藏
查看更多内容