Object Detection Models

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.

Source: FCOS: Fully Convolutional One-Stage Object Detection


Paper Code Results Date Stars


Task Papers Share
Object Detection 52 37.14%
Semantic Segmentation 13 9.29%
Instance Segmentation 12 8.57%
Pedestrian Detection 7 5.00%
Autonomous Driving 4 2.86%
Pseudo Label 3 2.14%
Domain Adaptation 3 2.14%
Pose Estimation 3 2.14%
Classification 3 2.14%