Corpus ID: 195346241

Sparsely Connected Convolutional Networks

@article{Zhu2018SparselyCC,
  title={Sparsely Connected Convolutional Networks},
  author={Ligeng Zhu and R. Deng and Zhiwei Deng and Greg Mori and P. Tan},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.05895}
}
Residual learning with skip connections permits training ultra-deep neural networks and obtains superb performance. Building in this direction, DenseNets proposed a dense connection structure where each layer is directly connected to all of its predecessors. The densely connected structure leads to better information flow and feature reuse. However, the overly dense skip connections also bring about the problems of potential risk of overfitting, parameter redundancy and large memory consumption… Expand
7 Citations
Super-Resolution Generator Networks: A comparative study
  • C. Lungu, R. Potolea
  • Computer Science
  • 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP)
  • 2018
AddressNet: Shift-Based Primitives for Efficient Convolutional Neural Networks
  • 14
Shift-based Primitives for Efficient Convolutional Neural Networks
  • 11
  • PDF
Deep Feature Aggregation Network for Hyperspectral Remote Sensing Image Classification
  • PDF
Learning temporal features of facial action units using deep learning
Vehicle Detection Under UAV Based on Optimal Dense YOLO Method
  • 17

References

SHOWING 1-10 OF 46 REFERENCES
Log-DenseNet: How to Sparsify a DenseNet
  • 18
  • Highly Influential
  • PDF
Densely Connected Convolutional Networks
  • 12,419
  • PDF
Dual Path Networks
  • 403
  • Highly Influential
  • PDF
Wide Residual Networks
  • 2,863
  • PDF
Deep Layer Aggregation
  • 354
  • PDF
Aggregated Residual Transformations for Deep Neural Networks
  • 3,418
  • PDF
Highway and Residual Networks learn Unrolled Iterative Estimation
  • 149
  • PDF
Identity Mappings in Deep Residual Networks
  • 4,544
  • Highly Influential
  • PDF
Deep Networks with Stochastic Depth
  • 960
  • PDF
...
1
2
3
4
5
...