Projects

Deep Learning

Architecture

 
  • Y. Li, Z. Kuang, Y. Chen and W. Zhang.
    Data-driven neuron allocation for scale aggregation networks.
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2019. [paper] [github]

    In this paper, we propose to learn the neuron allocation for aggregating multiscale information in different building blocks of a deep network. The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptivly allocated. Our scale aggregation network (ScaleNet) is constructed by repeating a scale aggregation (SA) block that concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations. The data-driven neuron allocation and SA block achieve strong representational power at the cost of considerably low computational complexity.

Applications

Locations of visitors to this page

profile counter Stats

Copyright © 2019 Wei Zhang