可逆的DenseNets与级联的LipSwish
Invertible DenseNets with Concatenated LipSwish
摘要：
我们引入可逆稠密网络（i-DenseNets），这是残差流的一个更有效的参数扩展。该方法依赖于对DenseNets中级联的Lipschitz连续性的分析，其中我们通过满足Lipschitz常数来强制网络的可逆性。此外，我们提出了一个可学习的加权级联，这不仅提高了模型的性能，但也表明了级联的加权表示的重要性。此外，我们引入了级联LipSwish作为激活函数，我们展示了如何执行Lipschitz条件并提高性能。新架构i-DenseNet在每维比特数评估的密度估计上优于残差流和其他基于流的模型，其中我们使用相等的参数预算。此外，我们证明了该模型在训练为混合模型时优于残差流，其中该模型既是生成模型又是判别模型。
英文摘要：
We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient extension of Residual Flows. The method relies on an analysis of the Lipschitz continuity of the concatenation in DenseNets, where we enforce invertibility of the network by satisfying the Lipschitz constant. Furthermore, we propose a learnable weighted concatenation, which not only improves the model performance but also indicates the importance of the concatenated weighted representation. Additionally, we introduce the Concatenated LipSwish as activation function, for which we show how to enforce the Lipschitz condition and which boosts performance. The new architecture, i-DenseNet, out-performs Residual Flow and other flow-based models on density estimation evaluated in bits per dimension, where we utilize an equal parameter budget. Moreover, we show that the proposed model out-performs Residual Flows when trained as a hybrid model where the model is both a generative and a discriminative model.
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。
