CenterNet: Objects as points中最终的预测是先给中心点加上偏移之后再计算边界

CenterNet的Head部分会预测三个变量：

    def forward_single(self, x: Tensor) -> Tuple[Tensor, ...]:
        """Forward feature of a single level.

        Args:
            x (Tensor): Feature of a single level.

        Returns:
            center_heatmap_pred (Tensor): center predict heatmaps, the
               channels number is num_classes.
            wh_pred (Tensor): wh predicts, the channels number is 2.
            offset_pred (Tensor): offset predicts, the channels number is 2.
        """
        center_heatmap_pred = self.heatmap_head(x).sigmoid()
        wh_pred = self.wh_head(x)
        offset_pred = self.offset_head(x)
        return center_heatmap_pred, wh_pred, offset_pred

分别是中心点热力图center_heatmap_pred，box宽高wh_pred ，与中心点偏移offset_pred

center_heatmap_pred 用来确定下图中的初始黄色点
wh_pred 用来预测下图中的红色宽高线段
offset_pred 用来预测下图中的(绿色)中心点偏移线段

直觉上也是先修正中心点，之后再根据box宽高确定box的位置，在代码中这样体现：

        topk_xs = topk_xs + offset[..., 0]
        topk_ys = topk_ys + offset[..., 1]
        tl_x = (topk_xs - wh[..., 0] / 2) * (inp_w / width)
        tl_y = (topk_ys - wh[..., 1] / 2) * (inp_h / height)
        br_x = (topk_xs + wh[..., 0] / 2) * (inp_w / width)
        br_y = (topk_ys + wh[..., 1] / 2) * (inp_h / height)

先重新修正变量topk_xs，之后再计算box的边界

以上代码均摘自 mmdet

https://github.com/open-mmlab/mmdetection/blob/main/mmdet/models/dense_heads/centernet_head.py