Matrix Nets: A New Deep Architecture for Object Detection

13 Aug 2019  ·  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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO test-dev MatrixNet Corners (ResNet-152, multi-scale) box mAP 47.8 # 108
AP50 66.2 # 68
AP75 52.3 # 58
APS 29.7 # 51
APM 50.4 # 54
APL 60.7 # 52
Hardware Burden None # 1
Operations per network pass None # 1

Methods