Papers › Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications

Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications

24 Mar 2018arXiv:1803.09127archive 2025-07-28

Zheng Qin, Zhaoning Zhang, Shiqing Zhang, Hao Yu, Yuxing Peng

Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these convolutions are more computationally economical. However, "sparsely-connected" convolutions block the inter-group information exchange, which induces severe performance degradation. To address this issue, we present two novel operations named merging and evolution to leverage the inter-group information. Our key idea is encoding the inter-group information with a narrow feature map, then combining the generated features with the original network for better representation. Taking advantage of the proposed operations, we then introduce the Merging-and-Evolution (ME) module, an architectural unit specifically designed for compact networks. Finally, we propose a family of compact neural networks called MENet based on ME modules. Extensive experiments on ILSVRC 2012 dataset and PASCAL VOC 2007 dataset demonstrate that MENet consistently outperforms other state-of-the-art compact networks under different computational budgets. For instance, under the computational budget of 140 MFLOPs, MENet surpasses ShuffleNet by 1% and MobileNet by 1.95% on ILSVRC 2012 top-1 accuracy, while by 2.3% and 4.1% on PASCAL VOC 2007 mAP, respectively.

PaperPDFCode

Code

clavichord93/MENet officialmentioned in papermentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT 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.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingMax PoolingMobileNetV1Pointwise ConvolutionReLUResidual ConnectionShuffleNetShuffleNet BlockSoftmax

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