超级会员免费看
本文探讨了目标检测中的多尺度分析，从单一图像/特征尺度的检测方法如Fast R-CNN和Faster R-CNN，到使用多层特征的SSD和MS-CNN。重点介绍了特征金字塔网络（Feature Pyramid Networks），它通过结合不同分辨率的特征图来改善对小物体的检测性能，避免了传统图像金字塔的不足。
单一图像/特征尺度的目标检测
Recent and more accurate detection methods like Fast R-CNN and Faster R-CNN advocate using features computed from a single scale, because it offers a good trade-off between accuracy and speed. Multi-scale detection, however, still performs better, especially for small objects.
使用多层特征的目标检测
SSD and MS-CNN predict objects at multiple layers of the feature hierachy without combining features or scores.
There are recent methods exploiting lateral/skip connections that associate low-level feature maps across resolutions and semantic levels, including U-Net and Sharp-Mask for segmentation,…Ghiasi et al. present a Laplacian pyramidal presentation for FCNs to progressively refine segmenta
订阅专栏 解锁全文
1296
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
