FCOS

2000년 도입 · 논문 80편에서 사용

FCOS is an anchor-box free, proposal free, single-stage object detection model. By eliminating the predefined set of anchor boxes, FCOS avoids computation related to anchor boxes such as calculating overlapping during training. It also avoids all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance.

출처: FCOS: Fully Convolutional One-Stage Object Detection

소개 논문: FCOS: Fully Convolutional One-Stage Object Detection