GhostNet V1 and V2: Lightweight CNN Architectures with Ghost Modules and Decoupled Attention
GhostNet introduces a novel approach to neural network lightweighting by rethinking how feature maps are generated—replacing expensive convolutions with structured, low-cost operations. Its evolution from V1 to V2 integrates spatial attention in a hardware-friendly manner, enabling stronger representational power without compromising inference ...
Posted on Wed, 07 Oct 2026 16:41:53 +0000 by sarijit