Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
IEEE Conference on Computer Vision and Pattern Recognition(2022)
摘要
Runtime and memory consumption are two important aspects for efficient image super-resolution (EISR) models to be deployed on resource-constrained devices. Recent advances in EISR [16, 32] exploit distillation and aggregation strategies with plenty of channel split and concatenation operations to fully use limited hierarchical features. In contrast, sequential network operations avoid frequently accessing preceding states and extra nodes, and thus are beneficial to reducing the memory consumption and runtime overhead. Following this idea, we design our lightweight network backbone by mainly stacking multiple highly optimized convolution and activation layers and decreasing the usage of feature fusion. We propose a novel sequential attention branch, where every pixel is assigned an important factor according to local and global contexts, to enhance high-frequency details. In addition, we tailor the residual block for EISR and propose an enhanced residual block (ERB) to further accelerate the network inference. Finally, combining all the above techniques, we construct a fast and memory-efficient network (FMEN) and its small version FMEN-S, which runs 33% faster and reduces 74% memory consumption compared with the state-of-the-art EISR model: E-RFDN, the champion in [49]. Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution [28]. Code is available at https://github.com/NJU-Jet/FMEN.
更多查看译文
关键词
runtime overhead,lightweight network backbone,optimized convolution,activation layers,novel sequential attention branch,enhanced residual block,network inference,fast memory-efficient network,74% memory consumption,state-of-the-art EISR model,lowest memory consumption,efficient super-resolution,runtime memory consumption,efficient image super-resolution models,resource-constrained devices,EISR [16],distillation,aggregation strategies,channel split,concatenation operations,sequential network operations
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要