Skip Connection Blocks

A Strided EESP unit is based on the EESP Unit but is modified to learn representations more efficiently at multiple scales. Depth-wise dilated convolutions are given strides, an average pooling operation is added instead of an identity connection, and the element-wise addition operation is replaced with a concatenation operation, which helps in expanding the dimensions of feature maps efficiently.

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


Paper Code Results Date Stars