将变分自编码器作为神经网络层，实现更灵活的生成建模。
Variational Autoencoder Layer
- 把VAE设计成可嵌入深层网络的模块化层
- 提出适配该层的新训练策略，提升模型性能
- 适合需要连续潜空间的生成任务研究者
变分自编码器（VAEs）是一类具有概率特性的自编码器，因其能生成平滑连续的潜在空间而广泛适用于数据生成。尽管该方法已问世十余年，仍被科研与工业界广泛采用。本文提出一种新思路：将VAE作为神经网络中的一个可嵌入层，而非独立模型。同时，针对包含此类层的模型设计了新的训练策略，并对其性能进行了全面分析。
原文摘要 · Abstract (English)
Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space. Despite being introduced over a decade ago, the method continues to be widely adopted in both research and industry for diverse applications. While VAEs are typically used as standalone models, this paper introduces a novel approach to integrate them as a neural network layer. Furthermore, a new training strategy is proposed for models incorporating these layers, and their performance is thoroughly analyzed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。