Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning

Yulun Zhang · Huan Wang · Can Qin · Yun Fu

[ Abstract ]
[ Visit Poster at Spot G1 in Virtual World ] [ OpenReview
Mon 25 Apr 10:30 a.m. PDT — 12:30 p.m. PDT

Abstract: Several image super-resolution (SR) networks have been proposed of late for efficient SR, achieving promising results. However, they are still not lightweight enough and neglect to be extended to larger networks. At the same time, model compression techniques, like neural architecture search and knowledge distillation, typically consume considerable computation resources. In contrast, network pruning is a cheap and effective model compression technique. However, it is hard to be applied to SR networks directly because filter pruning for residual blocks is well-known tricky. To address the above issues, we propose structure-regularized pruning (SRP), which imposes regularization on the pruned structure to ensure the locations of pruned filters are aligned across different layers. Specifically, for the layers connected by the same residual, we select the filters of the same indices as unimportant filters. To transfer the expressive power in the unimportant filters to the rest of the network, we employ $L_2$ regularization to drive the weights towards zero so that eventually, their absence will cause minimal performance degradation. We apply SRP to train efficient image SR networks, resulting in a lightweight network SRPN-Lite and a very deep one SRPN. We conduct extensive comparisons with both lightweight and larger networks. SRPN-Lite and SRPN perform favorably against other recent efficient SR approaches quantitatively and visually.

Chat is not available.