CVPR21最佳检测:不再是方方正正的目标检测输出(附源码)
计算机视觉研究院专栏
作者:Edison_G
有些目标往往具有任意方向的分布。因此,检测器需要更多的参数来编码方向信息,这往往是高度冗余和低效的...
论文:
https://openaccess.thecvf.com/content/CVPR2021/papers/Han_ReDet_A_Rotation-Equivariant_Detector_for_Aerial_Object_Detection_CVPR_2021_paper.pdf
源代码:
https: //github.com/csuhan/ReDet
1
简要
2
背景
3
新框架
(a) Overall architecture of the proposed Rotation-equivariant Detector. We first adopt the rotation-equivariant backbone to extract rotation-equivariant features, followed by an RPN and RoI Transformer (RT) to generate RRoIs. Then we use a novel Rotation-invariant RoI Align (RiRoI Align) to produce rotation-invariant features for RoI-wise classification and bounding box (bbox) regression.
(b) Rotation-equivariant feature maps. Under the cyclic group CN , the rotation-equivariant feature maps with the size (K, N, H, W ) have N orientation channels, and each orientation channel is corresponding to an element in CN .
(c)RiRoI Align. The proposed RiRoI Align consists of two parts: spatial alignment and orientation alignment. For an RRoI (x, y, w, h, θ), spatial alignment warps the RRoI from the spatial dimension, while orientation alignment circularly switches orientation channels and interpolates features to produce completely rotation-invariant features.
4
实验结果
转载请联系本公众号获得授权
计算机视觉研究院学习群等你加入!
扫码关注
计算机视觉研究院
公众号ID|ComputerVisionGzq
学习群|扫码在主页获取加入方式
往期推荐
🔗
Sparse R-CNN:稀疏框架,端到端的目标检测(附源码) 利用TRansformer进行端到端的目标检测及跟踪(附源代码) 细粒度特征提取和定位用于目标检测(附论文下载) 特别小的目标检测识别(附论文下载) 目标检测 | 基于统计自适应线性回归的目标尺寸预测 目标检测干货 | 多级特征重复使用大幅度提升检测精度(文末附论文下载) SSD7-FFAM | 对嵌入式友好的目标检测网络,为幼儿园儿童的安全保驾护航 目标检测新方式 | class-agnostic检测器用于目标检测(附论文下载链接) 干货 | 利用手持摄像机图像通过卷积神经网络实时进行水稻检测(致敬袁老) CVPR 2021 | 不需要标注了?看自监督学习框架如何助力目标检测