Corpus ID: 211069082

PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification

@article{Chen2020PixelHopAS,
  title={PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification},
  author={Yueru Chen and Mozhdeh Rouhsedaghat and Suya You and Raghuveer M. Rao and C.-C. Jay Kuo},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.03141}
}
  • Yueru Chen, Mozhdeh Rouhsedaghat, +2 authors C.-C. Jay Kuo
  • Published in ArXiv 2020
  • Computer Science, Engineering, Mathematics
  • The successive subspace learning (SSL) principle was developed and used to design an interpretable learning model, known as the PixelHop method,for image classification in our prior work. Here, we propose an improved PixelHop method and call it PixelHop++. First, to make the PixelHop model size smaller, we decouple a joint spatial-spectral input tensor to multiple spatial tensors (one for each spectral component) under the spatial-spectral separability assumption and perform the Saab transform… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES

    Learning Multiple Layers of Features from Tiny Images

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Interpretable Convolutional Neural Networks via Feedforward Design

    VIEW 2 EXCERPTS

    On Data-Driven Saak Transform

    VIEW 1 EXCERPT

    Reducing SqueezeNet Storage Size with Depthwise Separable Convolutions

    VIEW 1 EXCERPT