SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

Convolutional Neural Networks (CNNs) have achieved remarkable performance in various computer vision tasks but this comes at the cost of tremendous computational resources, partly due to convolutional layers extracting redundant features. Recent works either compress well-trained large-scale models or explore well-designed lightweight models. In this paper, we make an attempt to exploit spatial and channel redundancy among features for CNN compression and propose an efficient convolution module, called SCConv (Spatial and Channel reconstruction Convolution), to decrease redundant computing and facilitate representative feature learning. The proposed SCConv consists of two units: spatial reconstruction unit…

• NS
  Natural Science Foundation of Shanghai

  Award: 22ZR1421000
• SA
  Science and Technology Commission of Shanghai Municipality

  Award: 22DZ2229004
• NK
  National Key Research and Development Program of China

  Award: 2018AAA0100500