RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

Understand

Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design.

• Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers.
• Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible.
• To address this, this paper provides a new perspective to realize feature reuse implicitly and more efficiently instead of concatenation.