Abstract
Although most of the existing image super-resolution(SR)methods have achieved superior per-formance,contrastive learning for high-level tasks has not been fully utilized in the existing image SR methods based on deep learning.This work focuses on two well-known strategies developed for lightweight and robust SR,i.e.,contrastive learning and feedback mechanism,and proposes an in-tegrated solution called a split-based feedback network(SPFBN).The proposed SPFBN is based on a feedback mechanism to learn abstract representations and uses contrastive learning to explore high information in the representation space.Specifically,this work first uses hidden states and con-straints in recurrent neural network(RNN)to implement a feedback mechanism.Then,use cont-rastive learning to perform representation learning to obtain high-level information by pushing the fi-nal image to the intermediate images and pulling the final SR image to the high-resolution image.Besides,a split-based feedback block(SPFB)is proposed to reduce model redundancy,which tol-erates features with similar patterns but requires fewer parameters.Extensive experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.Moreover,this work extends the experiment to prove the effectiveness of this method and shows bet-ter overall reconstruction quality.
国家科技期刊平台
NSTL
万方数据