Papers › NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

16 Apr 2019CVPR 2019 6arXiv:1904.07392archive 2025-07-28

Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Search and discover a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections. The discovered architecture, named NAS-FPN, consists of a combination of top-down and bottom-up connections to fuse features across scales. NAS-FPN, combined with various backbone models in the RetinaNet framework, achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models. NAS-FPN improves mobile detection accuracy by 2 AP compared to state-of-the-art SSDLite with MobileNetV2 model in [32] and achieves 48.3 AP which surpasses Mask R-CNN [10] detection accuracy with less computation time.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

tensorflow/tpu mentioned on GitHubtf report
open-mmlab/mmdetection pytorchApache-2.0 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

Neural Architecture SearchObjectObject DetectionReal-Time Object Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: NAS-FPN

1x1 ConvolutionAmoebaNetAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionDropBlockFocal LossGlobal Average PoolingInverted Residual BlockKaiming InitializationLSTMMask R-CNNMax PoolingNAS-FPNPointwise ConvolutionRPNReLUResidual BlockResidual ConnectionRetinaNetRoIAlignSigmoid ActivationSoftmaxSpatially Separable ConvolutionStep DecayTanh 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