Papers › MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

2 Dec 2019CVPR 2020 6arXiv:1912.01106archive 2025-07-28

Bo Chen, Golnaz Ghiasi, Hanxiao Liu, Tsung-Yi Lin, Dmitry Kalenichenko, Hartwig Adams, Quoc V. Le

Despite the blooming success of architecture search for vision tasks in resource-constrained environments, the design of on-device object detection architectures have mostly been manual. The few automated search efforts are either centered around non-mobile-friendly search spaces or not guided by on-device latency. We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models. The learned MnasFPN head, when paired with MobileNetV2 body, outperforms MobileNetV3+SSDLite by 1.8 mAP at similar latency on Pixel. It is also both 1.0 mAP more accurate and 10% faster than NAS-FPNLite. Ablation studies show that the majority of the performance gain comes from innovations in the search space. Further explorations reveal an interesting coupling between the search space design and the search algorithm, and that the complexity of MnasFPN search space may be at a local optimum.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tensorflow/models officialmentioned in papermentioned on GitHubtf report
tensorflow/models 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

Object Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionEntropy RegularizationGlobal Average PoolingInverted Residual BlockLSTMNAS-FPNNeural Architecture SearchPPOPointwise ConvolutionReLUSigmoid ActivationSoftmaxTanh Activation

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