paper-with-me

홈 › Papers

Invertible Residual Networks

2018-11-02 · Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen

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.

📄 PDF Abstract BibTeX arXiv:1811.00995

Code (5)

RuqiBai/mixture_flow pytorch
eyalbetzalel/residual-flows pytorch
jhjacobsen/invertible-resnet pytorch
rtqichen/residual-flows pytorch
yperugachidiaz/invertible_densenets pytorch

Tasks

Density EstimationGeneral ClassificationImage Generation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Invertible Residual Network with Regularization for Effective Medical Image Segmentation

2021-03-16 · Kashu Yamazaki, Vidhiwar Singh Rathour, T. Hoang Ngan Le

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 Segmentation

Residual Flows for Invertible Generative Modeling

2019-06-06 · NeurIPS 2019 12 · Ricky T. Q. Chen, Jens Behrmann, David Duvenaud, Jörn-Henrik Jacobsen

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 Generation

Graph Residual Flow for Molecular Graph Generation

2019-09-30 · Shion Honda, Hirotaka Akita, katsuhiko Ishiguro, Toshiki Nakanishi 외

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 Generation

The sampling complexity of learning invertible residual neural networks

2024-11-08 · Yuanyuan Li, Philipp Grohs, Philipp Petersen

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

2024-05-05 · Jinmin Li, Tao Dai, Yaohua Zha, Yilu Luo 외

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