Papers › Matrix Nets: A New Deep Architecture for Object Detection

Matrix Nets: A New Deep Architecture for Object Detection

13 Aug 2019arXiv:1908.04646archive 2025-07-28

Abdullah Rashwan, Agastya Kalra, Pascal Poupart

We present Matrix Nets (xNets), a new deep architecture for object detection. xNets map objects with different sizes and aspect ratios into layers where the sizes and the aspect ratios of the objects within their layers are nearly uniform. Hence, xNets provide a scale and aspect ratio aware architecture. We leverage xNets to enhance key-points based object detection. Our architecture achieves mAP of 47.8 on MS COCO, which is higher than any other single-shot detector while using half the number of parameters and training 3x faster than the next best architecture.

PaperPDFCode

Code

arashwan/matrixnet mentioned on GitHubpytorch report
lizhe960118/CenterNet 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

ObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) AP50 66.2 #114 of 225 Archive leaderboard report
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) AP75 52.3 #114 of 225 Archive leaderboard report
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) APL 60.7 #114 of 225 Archive leaderboard report
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) APM 50.4 #114 of 225 Archive leaderboard report
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) APS 29.7 #114 of 225 Archive leaderboard report
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) box mAP 47.8 #114 of 225 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual 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