paper-with-me

홈 › Papers

m-RevNet: Deep Reversible Neural Networks with Momentum

2021-08-12 · Duo Li, Shang-Hua Gao

In recent years, the connections between deep residual networks and first-order Ordinary Differential Equations (ODEs) have been disclosed. In this work, we further bridge the deep neural architecture design with the second-order ODEs and propose a novel reversible neural network, termed as m-RevNet, that is characterized by inserting momentum update to residual blocks. The reversible property allows us to perform backward pass without access to activation values of the forward pass, greatly relieving the storage burden during training. Furthermore, the theoretical foundation based on second-order ODEs grants m-RevNet with stronger representational power than vanilla residual networks, which potentially explains its performance gains. For certain learning scenarios, we analytically and empirically reveal that our m-RevNet succeeds while standard ResNet fails. Comprehensive experiments on various image classification and semantic segmentation benchmarks demonstrate the superiority of our m-RevNet over ResNet, concerning both memory efficiency and recognition performance.

📄 PDF Abstract BibTeX arXiv:2108.05862

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationSemantic Segmentation

Methods 이 논문이 사용한 방법론

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…
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
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…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Similar Papers 제목 키워드 기반

Training Generative Reversible Networks

2018-06-05 · Robin Tibor Schirrmeister, Patryk Chrabąszcz, Frank Hutter, Tonio Ball

Generative models with an encoding component such as autoencoders currently receive great interest. However, training of autoencoders is typically complicated by the need to train a separate encoder and decoder model tha…

Decoder

CrevNet: Conditionally Reversible Video Prediction

2019-10-25 · Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler

Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Con…

Computational EfficiencyPredictionVideo Prediction

The Reversible Residual Network: Backpropagation Without Storing Activations

2017-07-14 · NeurIPS 2017 12 · Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse

Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. However, memory consumption becomes a bot…

General Classificationimage-classificationImage Classification

Efficient and Information-Preserving Future Frame Prediction and Beyond

2020-05-01 · ICLR 2020 1 · Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler

Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Con…

Computational Efficiencyobject-detectionObject DetectionPrediction+2

Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation

2021-12-02 · Yuankai Teng, Zhu Wang, Lili Ju, Anthony Gruber 외

Due to the curse of dimensionality and the limitation on training data, approximating high-dimensional functions is a very challenging task even for powerful deep neural networks. Inspired by the Nonlinear Level set Lear…

Dimensionality Reductionregressionsubspace methods