Sai-Hong Li

MobileCrackNet: lightweight crack segmentation with mobile encoder and channel attention

Crack segmentation is critical for civil infrastructure inspection, yet state-of-the-art methods such as MixerCSeg rely on complex State Space Model (SSM) encoders with custom CUDA kernels that limit portability. We propose MobileCrackNet, a lightweight alternative that replaces the SSM encoder with a MobileNetV2 backb...