Papers › MoGA: Searching Beyond MobileNetV3

MoGA: Searching Beyond MobileNetV3

4 Aug 2019arXiv:1908.01314archive 2025-07-28

Xiangxiang Chu, Bo Zhang, Ruijun Xu

The evolution of MobileNets has laid a solid foundation for neural network applications on mobile end. With the latest MobileNetV3, neural architecture search again claimed its supremacy in network design. Unfortunately, till today all mobile methods mainly focus on CPU latencies instead of GPU, the latter, however, is much preferred in practice for it has faster speed, lower overhead and less interference. Bearing the target hardware in mind, we propose the first Mobile GPU-Aware (MoGA) neural architecture search in order to be precisely tailored for real-world applications. Further, the ultimate objective to devise a mobile network lies in achieving better performance by maximizing the utilization of bounded resources. Urging higher capability while restraining time consumption is not reconcilable. We alleviate the tension by weighted evolution techniques. Moreover, we encourage increasing the number of parameters for higher representational power. With 200x fewer GPU days than MnasNet, we obtain a series of models that outperform MobileNetV3 under the similar latency constraints, i.e., MoGA-A achieves 75.9% top-1 accuracy on ImageNet, MoGA-B meets 75.5% which costs only 0.5 ms more on mobile GPU. MoGA-C best attests GPU-awareness by reaching 75.3% and being slower on CPU but faster on GPU.The models and test code is made available here https://github.com/xiaomi-automl/MoGA.

PaperPDFCode

Code

xiaomi-automl/MoGA officialmentioned in papermentioned on GitHubpytorch report
baiyancheng20/gaga mentioned on GitHubpytorch 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

AutoMLImage ClassificationNeural Architecture Search

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MoGA-A GFLOPs 0.608 #929 of 1060 Archive leaderboard report
Image Classification ImageNet MoGA-A Number of params 5.1M #929 of 1060 Archive leaderboard report
Image Classification ImageNet MoGA-A Operations per network pass 0.0304G #929 of 1060 Archive leaderboard report
Image Classification ImageNet MoGA-A Top 1 Accuracy 75.9% #929 of 1060 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

Introduced by this paper: MoGA-B, MoGA-C

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionCosine AnnealingDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGlobal Average PoolingHard SwishInverted Residual BlockLinear WarmupMoGA-AMoGA-BMoGA-CPointwise ConvolutionRMSPropReLUReLU6SGD with MomentumSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockWeight Decay

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