Invertible Residual Networks
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.
Code (5)
Tasks
Density EstimationGeneral ClassificationImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Invertible Residual Network with Regularization for Effective Medical Image Segmentation
Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly ofte…
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationResidual Flows for Invertible Generative Modeling
Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations…
Density EstimationImage GenerationGraph Residual Flow for Molecular Graph Generation
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics. Among these models, invertible flow-based approaches are not fully explored yet. I…
Graph GenerationMolecular Graph GenerationThe sampling complexity of learning invertible residual neural networks
In recent work it has been shown that determining a feedforward ReLU neural network to within high uniform accuracy from point samples suffers from the curse of dimensionality in terms of the number of samples needed. As…
Invertible Residual Rescaling Models
Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling. However, we observe that IRNs with deeper networks are difficult to t…
Image Rescaling