Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
FreNet is proposed, a feature reconfiguration framework with visual priors, which performs pixel-level reconfiguration before encoding and feature-level reconfiguration during encoding for precise medical lesion segmentation and significantly outperforms state-of-the-art methods.
Yi-Nan Liu, Jian-Kang Hong, Zhen Gao et al.
· 0 citations