Papers › MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution

MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution

29 Nov 2018arXiv:1811.12043archive 2025-07-28

Jun-Hyuk Kim, Jun-Ho Choi, Manri Cheon, Jong-Seok Lee

In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to various characteristics of images, which limits their representational capability and, consequently, results in unnecessarily large model sizes. To address this issue, we propose a novel multi-path adaptive modulation network (MAMNet). Specifically, we propose a multi-path adaptive modulation block (MAMB), which is a lightweight yet effective residual block that adaptively modulates residual feature responses by fully exploiting their information via three paths. The three paths model three types of information suitable for SR: 1) channel-specific information (CSI) using global variance pooling, 2) inter-channel dependencies (ICD) based on the CSI, 3) and channel-specific spatial dependencies (CSD) via depth-wise convolution. We demonstrate that the proposed MAMB is effective and parameter-efficient for image SR than other feature modulation methods. In addition, experimental results show that our MAMNet outperforms most of the state-of-the-art methods with a relatively small number of parameters.

PaperPDFCode

Code

junhyukk/MAMNet-Tensorflow officialmentioned in papermentioned on GitHubtf report
S-aiueo32/SRRAM mentioned on GitHubtf report
manricheon/MAMNet-Tensorflow-2 mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 4x upscaling SRRAM PSNR 27.56 #34 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SRRAM SSIM 0.7350 #34 of 71 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SRRAM PSNR 28.54 #60 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SRRAM SSIM 0.7800 #60 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SRRAM PSNR 26.05 #43 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SRRAM SSIM 0.7834 #43 of 65 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationConvolutionReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections