Matrix Nets: A New Deep Architecture for Object Detection
- Resource Type
- Conference
- Authors
- Rashwan, Abdullah; Kalra, Agastya; Poupart, Pascal
- Source
- 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) ICCVW Computer Vision Workshop (ICCVW), 2019 IEEE/CVF International Conference on. :2025-2028 Oct, 2019
- Subject
- Computing and Processing
Object detection
Computer architecture
Detectors
Heating systems
Training
Kernel
Computer vision
object detection
neural architecture
- Language
- ISSN
- 2473-9944
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.