M2Det

2000년 도입 · 논문 2편에서 사용

M2Det is a one-stage object detection model that utilises a Multi-Level Feature Pyramid Network (MLFPN) to extract features from the input image, and then similar to SSD, produces dense bounding boxes and category scores based on the learned features, followed by the non-maximum suppression (NMS) operation to produce the final results.

출처: M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

소개 논문: M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network