Moreover, we also show together with our proposed center-ness branch, the much simpler detector can achieve even better detection performance than its anchorbased counterparts.
The detector directly views locations as training samples instead of anchor boxes in anchor-based detectors, which is the same as FCNs for semantic segmentation.
center-ness 的作用
抑制低质量的检测边框,提升检测性能。
Finally, we present our proposed “centerness” branch, which helps suppress the low-quality detected bounding boxes and improves the overall performance by a large margin.