Matrix Nets: A New Deep Architecture for Object Detection
This improves object detection accuracy and efficiency for computer vision applications, though it appears incremental as it builds on key-points based detection.
The paper tackles object detection by introducing Matrix Nets (xNets), a deep architecture that maps objects to layers based on size and aspect ratio uniformity, achieving 47.8 mAP on MS COCO with half the parameters and 3x faster training than the next best single-shot detector.
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.