双向VAE用同一网络双向编码解码,参数减半还更优。
Bidirectional Variational Autoencoders
- 同一网络正向编码反向解码,共享权重减少参数。
- 在四类图像任务中参数量减半,性能略超传统VAE。
- 适合追求高效模型且需生成与重建能力的场景。
我们提出新型双向变分自编码器(BVAE)架构。BVAE使用单一神经网络同时完成编码与解码,而非传统的编码器-解码器配对结构。该网络通过相同的突触连接,正向进行编码,反向实现解码。模拟实验对比了BVAE与普通VAE在四类图像任务上的表现:图像重建、分类、插值和生成。所用数据集包括MNIST手写数字、Fashion-MNIST、CIFAR-10和CelebA-64人脸图像。结果显示,BVAE的双向结构使参数量减少近50%,同时在各项任务中仍略优于单向VAE。
原文摘要 · Abstract (English)
We present the new bidirectional variational autoencoder (BVAE) network architecture. The BVAE uses a single neural network both to encode and decode instead of an encoder-decoder network pair. The network encodes in the forward direction and decodes in the backward direction through the same synaptic web. Simulations compared BVAEs and ordinary VAEs on the four image tasks of image reconstruction, classification, interpolation, and generation. The image datasets included MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and CelebA-64 face images. The bidirectional structure of BVAEs cut the parameter count by almost 50% and still slightly outperformed the unidirectional VAEs.
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。