FPN自底向上的通路增强

最新推荐文章于 2024-09-04 12:00:13 发布

Gallant Hu

最新推荐文章于 2024-09-04 12:00:13 发布

阅读量385

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/113760316

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

本文介绍了FPN（Feature Pyramid Networks）的增强方法，包括自底向上的路径增强，使得低层信息更容易传播，以及自适应特征池化，允许每个提案从所有级别获取信息进行预测，提升性能。该框架独立于CNN结构，适用于多种场景。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在这里插入图片描述
Our framework is illustrated in Figure 1. Path augmentation and aggregation are conducted for improving performance. A bottom-up path is augmented to make low-layer information easier to propagate. We design adaptive feature pooling to allow each proposal to access information from all levels for prediction.

A complementary path is added to the mask-prediction branch. This new structure leads to decent performance. Similar to FPN, the improvement is independent of the CNN structures, such as those of [57, 32, 23].