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}
}
  • Saining Xie, Ross B. Girshick, +2 authors Kaiming He
  • Published 2017
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 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
    3,140 Citations

    Figures, Tables, and Topics from this paper

    Learning Strict Identity Mappings in Deep Residual Networks
    • 24
    • PDF
    Sequentially Aggregated Convolutional Networks
    • Highly Influenced
    • PDF
    Learning Transferable Architectures for Scalable Image Recognition
    • 2,116
    • PDF
    Gated Convolutional Networks with Hybrid Connectivity for Image Classification
    • 9
    • PDF
    Data-Driven Sparse Structure Selection for Deep Neural Networks
    • 185
    • Highly Influenced
    • PDF
    Dual Path Networks
    • 381
    • Highly Influenced
    • PDF
    Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
    • 55
    • PDF
    Rethinking Binary Neural Network for Accurate Image Classification and Semantic Segmentation
    • 1
    • Highly Influenced
    Batch Normalization with Enhanced Linear Transformation
    • Highly Influenced
    • PDF
    MultiGrain: a unified image embedding for classes and instances
    • 11
    • PDF

    References

    SHOWING 1-10 OF 59 REFERENCES
    Wide Residual Networks
    • 2,659
    • PDF
    Understanding Deep Architectures using a Recursive Convolutional Network
    • 112
    • PDF
    Going deeper with convolutions
    • 21,810
    • Highly Influential
    • PDF
    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
    • 8,832
    • PDF
    Identity Mappings in Deep Residual Networks
    • 4,288
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 43,557
    • Highly Influential
    • PDF
    Deep Residual Learning for Image Recognition
    • 57,702
    • PDF
    DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
    • 3,683
    • PDF
    Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
    • 113
    • PDF
    Rethinking the Inception Architecture for Computer Vision
    • 9,879
    • Highly Influential
    • PDF