You're currently viewing an old version of this dataset. To see the current version, click here.

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations.

Data and Resources

Cite this as

Xudong Wang, Stella X. Yu (2024). Dataset: Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters. https://doi.org/10.57702/12fz1k8m

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2009.12021
Author Xudong Wang
More Authors
Stella X. Yu
Homepage https://arxiv.org/abs/2004.08955