An EESP Unit, or Extremely Efficient Spatial Pyramid of Depth-wise Dilated Separable Convolutions, is an image model block designed for edge devices. It was proposed as part of the ESPNetv2 CNN architecture.

This building block is based on a reduce-split-transform-merge strategy. The EESP unit first projects the high-dimensional input feature maps into low-dimensional space using groupwise pointwise convolutions and then learns the representations in parallel using depthwise dilated separable convolutions with different dilation rates. Different dilation rates in each branch allow the EESP unit to learn the representations from a large effective receptive field. To remove the gridding artifacts caused by dilated convolutions, the EESP fuses the feature maps using hierarchical feature fusion (HFF).

Source: ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

Latest Papers

PAPER DATE
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
| Sachin MehtaMohammad RastegariLinda ShapiroHannaneh Hajishirzi
2018-11-28

Categories