SBNet: Sparse Blocks Network for Fast Inference

@article{Ren2018SBNetSB,
  title={SBNet: Sparse Blocks Network for Fast Inference},
  author={Mengye Ren and A. Pokrovsky and B. Yang and R. Urtasun},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={8711-8720}
}
Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such as object detection and semantic segmentation, we are able to obtain a low-cost computation mask, either from a priori problem knowledge, or from a low-resolution segmentation network. We show that such computation masks can be used to reduce computation in… Expand
78 Citations
Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
  • 10
  • PDF
SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
  • 17
  • PDF
Adaptive Structured Sparse Network for Efficient CNNs with Feature Regularization
Learning Instance-wise Sparsity for Accelerating Deep Models
  • 6
  • PDF
Acorns: A Framework for Accelerating Deep Neural Networks with Input Sparsity
  • X. Dong, Lei Liu, +4 authors Xiaobing Feng
  • Computer Science
  • 2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT)
  • 2019
  • 6
  • Highly Influenced
Deep Adaptive Inference Networks for Single Image Super-Resolution
  • 3
  • PDF
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions
  • PDF
Batch-shaping for learning conditional channel gated networks
  • 14
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
Sparse Convolutional Neural Networks
  • 498
  • PDF
Sparsity Invariant CNNs
  • 290
  • PDF
Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
  • 126
  • PDF
Pruning Filters for Efficient ConvNets
  • 1,457
  • PDF
Learning Structured Sparsity in Deep Neural Networks
  • 1,196
  • PDF
Speeding up Convolutional Neural Networks with Low Rank Expansions
  • 938
  • PDF
Submanifold Sparse Convolutional Networks
  • 108
  • Highly Influential
  • PDF
Fast Algorithms for Convolutional Neural Networks
  • Andrew Lavin, Scott Gray
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
  • 490
  • PDF
Spatially Adaptive Computation Time for Residual Networks
  • 179
  • PDF
Channel Pruning for Accelerating Very Deep Neural Networks
  • Yihui He, X. Zhang, Jian Sun
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
  • 984
  • PDF
...
1
2
3
4
...