CR-VAE：用于防止后验坍塌的变分自编码器对比正则化
CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse
AI总结：
针对VAE因目标函数局限导致的后验坍塌问题，提出CR-VAE方法，通过引入对比目标最大化相似输入间互信息，有效防止后验坍塌并在视觉数据集上优于现有方法。
摘要：
变分自编码器（VAE）已知会受到后验坍塌现象的影响，即模型生成的潜在表示变得与输入相互独立。这会导致输入的表示退化，该问题归因于VAE目标函数的局限性。在本研究中，我们针对该问题提出了一种新颖的解决方案，即变分自编码器的对比正则化（CR-VAE）。我们方法的核心是通过引入对比目标来增强原始VAE，该对比目标旨在最大化相似视觉输入表示之间的互信息。这一策略确保了输入与其潜在表示之间的信息流最大化，从而有效避免了后验坍塌。我们在一系列视觉数据集上评估了该方法，并证明CR-VAE在防止后验坍塌方面优于现有最先进的方法。
英文摘要：
The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of the input, which is attributed to the limitations of the VAE's objective function. In this work, we propose a novel solution to this issue, the Contrastive Regularization for Variational Autoencoders (CR-VAE). The core of our approach is to augment the original VAE with a contrastive objective that maximizes the mutual information between the representations of similar visual inputs. This strategy ensures that the information flow between the input and its latent representation is maximized, effectively avoiding posterior collapse. We evaluate our method on a series of visual datasets and demonstrate, that CR-VAE outperforms state-of-the-art approaches in preventing posterior collapse.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
