Aggregated Residual Transformations for Deep Neural Networks

@article{Xie2017AggregatedRT,
  title={Aggregated Residual Transformations for Deep Neural Networks},
  author={Saining Xie and Ross B. Girshick and Piotr Doll{\'a}r and Zhuowen Tu and Kaiming He},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={5987-5995}
}
We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call cardinality (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 789 CITATIONS, ESTIMATED 79% COVERAGE

Dynamic Multi-path Neural Network

VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Feature Selective Anchor-Free Module for Single-Shot Object Detection

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Late Fusion via Subspace Search With Consistency Preservation

  • IEEE Transactions on Image Processing
  • 2019
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Libra R-CNN: Towards Balanced Learning for Object Detection

  • ArXiv
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Action Recognition with Dynamic Image Networks

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Analysis on Temporal Dimension of Inputs for 3D Convolutional Neural Networks

  • 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS)
  • 2018
VIEW 10 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

CUImage: A Neverending Learning Platform on a Convolutional Knowledge Graph of Billion Web Images

  • 2018 IEEE International Conference on Big Data (Big Data)
  • 2018
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Deep Layer Aggregation

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 9 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 185 Highly Influenced Citations

  • Averaged 191 Citations per year over the last 3 years

  • 67% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 46 REFERENCES

Inception-v4

C. Szegedy, S. Ioffe, V. Vanhoucke
  • inception-resnet and the impact of residual connections on learning. In ICLR Workshop
  • 2016
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Rethinking the Inception Architecture for Computer Vision

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet Large Scale Visual Recognition Challenge

  • International Journal of Computer Vision
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Training and investigating Residual Nets

S. Gross, M. Wilber
  • https://github.com/ facebook/fb.resnet.torch
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…