FCOS中基于FPN的多尺度预测--FCOSHead

最新推荐文章于 2024-10-14 21:39:57 发布

Gallant Hu

最新推荐文章于 2024-10-14 21:39:57 发布

阅读量562

点赞数

CC 4.0 BY-SA版权

分类专栏：目标检测从基础到实践--系列论文讲解

本文链接：https://blog.youkuaiyun.com/weixin_42108090/article/details/109769486

目标检测从基础到实践--系列论文讲解专栏收录该内容

53 篇文章 ¥59.90 ¥99.00

订阅专栏

超级会员免费看

FCOS是一种基于FCN的检测器，尽管其特征映射的步长可能导致看似较低的边界框召回率（BPR），但实验证明，即使在大步长下，FCOS仍能实现良好的BPR，甚至优于RetinaNet在Detectron中的实现。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Here BPR is defined as the ratio of the number of ground-truth boxes a detector can recall at the most divided by all ground-truth boxes.
For FCOS, at the first glance one may think that the BPR can be much lower than anchor-based detectors because it is impossible to recall an object which no location on the final feature maps encodes due to a large stride. Here, we empirically show that even with a large stride, FCN-based FCOS is still able to produce a good BPR, and it can even better than the BPR of the anchor-based detector RetinaNet [15] in the official implementation Detectron [7] (refer to Table 1).