m-RevNet: A Novel Recursive Neural Network Based on Second-Order Ordinary Differential Equations

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Added to collectionTop 100 Deep Learning and AI Papers 2021

m-RevNet: A Novel Recursive Neural Network Based on Second-Order Ordinary Differential Equations

m-RevNet: Deep Reversible Neural Networks with Momentum

We propose a novel reversible neural network, termed as m-revnet, that is characterized by inserting momentum update to residualblocks.

The reversible property allows us to perform backward pass without access to activation values of the forward pass, greatly relieving the storageburden during training.

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 standard resnet, concerning both memory efficiency and recognition performance.

Authors

Duo Li, Shang-Hua Gao

◐ Recommended Follows

◐ Latest Activity