Corpus ID: 12130626

Training Deeper Convolutional Networks with Deep Supervision

@article{Wang2015TrainingDC,
  title={Training Deeper Convolutional Networks with Deep Supervision},
  author={Liwei Wang and Chen-Yu Lee and Zhuowen Tu and Svetlana Lazebnik},
  journal={ArXiv},
  year={2015},
  volume={abs/1505.02496}
}
  • Liwei Wang, Chen-Yu Lee, +1 author Svetlana Lazebnik
  • Published 2015
  • Computer Science
  • ArXiv
  • One of the most promising ways of improving the performance of deep convolutional neural networks is by increasing the number of convolutional layers. [...] Key Method We formulate a simple rule of thumb to determine where these branches should be added. The resulting deeply supervised structure makes the training much easier and also produces better classification results on ImageNet and the recently released, larger MIT Places datasetExpand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 69 CITATIONS

    Novel CNN architecture with residual learning and deep supervision for large-scale scene image categorization

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Residual CNDS

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Residual Squeeze VGG16

    VIEW 3 EXCERPTS
    CITES METHODS

    Large-scale scene image categorisation with deep learning-based model

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Residual-CNDS for Grand Challenge Scene Dataset

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Residual squeeze CNDS deep learning CNN model for very large scale places image recognition

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Application of deep learning to computer vision: A comprehensive study

    VIEW 1 EXCERPT
    CITES METHODS

    FILTER CITATIONS BY YEAR

    2015
    2020

    CITATION STATISTICS

    • 8 Highly Influenced Citations

    • Averaged 13 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 13 REFERENCES

    Deeply-Supervised Nets

    VIEW 5 EXCERPTS

    Going deeper with convolutions

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Visualizing and Understanding Convolutional Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Caffe: Convolutional Architecture for Fast Feature Embedding

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    ImageNet Large Scale Visual Recognition Challenge

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL