We show that standard ResNet architectures can be made invertible, allowing
the same model to be used for classification, density estimation, and
generation. Typically, enforcing invertibility requires partitioning dimensions
or restricting network architectures. In contrast, our approach only requires
adding a simple normalization step during training, already available in
standard frameworks. Invertible ResNets define a generative model which can be
trained by maximum likelihood on unlabeled data. To compute likelihoods, we
introduce a tractable approximation to the Jacobian log-determinant of a
residual block. Our empirical evaluation shows that invertible ResNets perform
competitively with both state-of-the-art image classifiers and flow-based
generative models, something that has not been previously achieved with a
single architecture.

本研究展示了传统的 ResNet 模型可以被做成可逆的，这意味着同一个模型可以同时用于分类、密度估计和生成。令人惊讶的是，我们的方法只需要在训练时增加一个简单的归一化步骤，而不需要将维度分割或限制网络结构。作为一种生成模型，可逆的 ResNet 可以通过无标签数据的最大似然估计进行训练。为了计算似然，我们引入了一个可计算的对余块 Jacobian 行列式对数的近似值。实验证明，可逆 ResNet 在严格意义下表现出色，达到了同一个架构内同时具有现有最先进图像分类器和流式生成模型的性能。