Robust feature knowledge distillation for enhanced performance of lightweight crack segmentation models

arXiv:2404.06258v1 Announce Type: new
Abstract: Vision-based crack detection faces deployment challenges due to the size of robust models and edge device limitations. These can be addressed with lightweight models trained with knowledge distillation (KD). However, state-of-the-art (SOTA) KD methods compromise anti-noise robustness. This paper develops Robust Feature Knowledge Distillation (RFKD), a framework to improve robustness while retaining the precision of light models for crack segmentation. RFKD distils knowledge from a teacher model's logit layers and intermediate feature maps while leveraging …

abstract art arxiv challenges cs.cv deployment detection distillation edge feature however knowledge limitations noise paper performance robust robust models robustness segmentation sota state type vision