# Matrix Nets: A New Deep Architecture for Object Detection

## TL;DR

Matrix Nets (xNets) introduce a scale and aspect ratio aware deep architecture for object detection, achieving state-of-the-art accuracy with fewer parameters and faster training times.

## Contribution

The paper proposes Matrix Nets (xNets), a novel deep architecture that effectively handles objects of various sizes and aspect ratios, improving detection performance.

## Key findings

- Achieves 47.8 mAP on MS COCO
- Uses half the parameters of comparable models
- Trains three times faster than similar architectures

## Abstract

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.