mmdetection(7): Region Proposal by Guided Anchoring

最新推荐文章于 2025-07-09 10:43:19 发布

冷夏LX

最新推荐文章于 2025-07-09 10:43:19 发布

阅读量1.5k

点赞数 1

CC 4.0 BY-SA版权

分类专栏：检测算法-深度学习

本文链接：https://blog.youkuaiyun.com/u014119694/article/details/93738008

检测算法-深度学习专栏收录该内容

35 篇文章

订阅专栏

在这里插入图片描述

这篇文章解决了anchor手动生成的问题，
其想法也很简单，
在最近的论文中，产生了一种类似利用分割图的思想，比如FSAF，很有意思
这篇文章就是利用如上的思想，
原始框架如上图所示，
不过是把原来的RPN改为Guide anchoring，都是产生anchor和原始特征图。

Faster-RCNN是根据anchor产生的，该文则是直接预测每个点是否是anchor中心点。如下图所示：

在这里插入图片描述
对于每个点还应预测其anchor 的高度和宽度，
当然与fater rcnn不同的是，rpga 的feature map不再是原图，而是通过卷积后的图，即feature adaption，通过一个dcn来获取更多的特征信息。

class FeatureAdaption(nn.Module): #DCN操作
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=3,
                 deformable_groups=4):
        super(FeatureAdaption, self).__init__()
        offset_channels = kernel_size * kernel_size * 2
        self.conv_offset = nn.Conv2d(
            2, deformable_groups * offset_channels, 1, bias=False)
        self.conv_adaption = DeformConv(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            padding=(kernel_size - 1) // 2,
            deformable_groups=deformable_groups)
        self.relu = nn.ReLU(inplace=True)

    def init_weights(self):
        normal_init(self.conv_offset, std=0.1)
        normal_init(self.conv_adaption, std=0.01)

    def forward(self, x, shape):
        offset = self.conv_offset(shape.detach())
        x = self.relu(self.conv_adaption(x, offset))
        return x


def _init_layers(self):
      self.relu = nn.ReLU(inplace=True)
      self.conv_loc = nn.Conv2d(self.feat_channels, 1, 1) #预测中心点
      self.conv_shape = nn.Conv2d(self.feat_channels, self.num_anchors * 2,
                                  1)#预测宽高
      self.feature_adaption = FeatureAdaption(
          self.feat_channels,
          self.feat_channels,
          kernel_size=3,
          deformable_groups=self.deformable_groups)
      self.conv_cls = MaskedConv2d(self.feat_channels,
                                   self.num_anchors * self.cls_out_channels,
                                   1)
      self.conv_reg = MaskedConv2d(self.feat_channels, self.num_anchors * 4,
                                   1)
def forward_single(self, x):
        loc_pred = self.conv_loc(x)
        shape_pred = self.conv_shape(x)
        x = self.feature_adaption(x, shape_pred)
        # masked conv is only used during inference for speed-up
        if not self.training:
            mask = loc_pred.sigmoid()[0] >= self.loc_filter_thr
        else:
            mask = None
        cls_score = self.conv_cls(x, mask)
        bbox_pred = self.conv_reg(x, mask)
        return cls_score, bbox_pred, shape_pred, loc_pred