方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 可解释变分自编码器× | 多模态变分自编码器× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2013–2017 | 2018 |
| 提出者≠ | Kingma, D. P. & Welling, M. (VAE); Higgins et al. (beta-VAE for disentanglement) | Wu, M. and Goodman, N. |
| 类型≠ | Generative model with interpretable latent space | Generative latent-variable model |
| 开创性文献≠ | Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014). link ↗ | Wu, M., & Goodman, N. (2018). Multimodal Generative Models for Scalable Weakly-Supervised Learning. Advances in Neural Information Processing Systems (NeurIPS), 31. link ↗ |
| 别名 | XVAE, Interpretable VAE, Disentangled Variational Autoencoder, Explainable Generative Model | MVAE, multimodal VAE, multi-modal variational autoencoder, multimodal generative model |
| 相关≠ | 4 | 3 |
| 摘要≠ | An Explainable Variational Autoencoder (XVAE) extends the standard VAE framework with techniques that make its latent space interpretable: disentangling latent dimensions so each corresponds to a human-understandable factor, or post-hoc attribution methods (SHAP, integrated gradients) that trace reconstructions back to input features. It retains the VAE's generative power while adding transparency required in scientific and high-stakes applications. | The Multimodal Variational Autoencoder (MVAE) is a deep generative model that learns a shared latent representation across two or more data modalities — such as images and captions — using a product-of-experts fusion of modality-specific encoders, enabling generation and inference even when only a subset of modalities is observed at test time. |
| ScholarGate数据集 ↗ |
|
|