SoftIoU Loss

SoftIoU.md

自己实现的 SoftIoU Loss，用于前景背景的图像分割，相较于 Focal Loss，SoftIoU Loss 的好处是不需要设置 Loss 的参数了，只要关注 Model 就好了

from gluoncv.loss import Loss as gcvLoss

class SoftIoULoss(gcvLoss):
    def __init__(self, batch_axis=0, weight=None):
        super(SoftIoULoss, self).__init__(weight, batch_axis)

    def hybrid_forward(self, F, pred, target):
        pred = F.sigmoid(pred)
        smooth = 1
        intersection = pred * target
        loss = (intersection.sum() + smooth) / (pred.sum() + target.sum() -
                                                intersection.sum() + smooth)
        loss = 1 - loss

        return loss

您好，请问将SoftIoU Loss应用在红外小目标分割有什么好处吗？

正负样本太过不平衡的情况下，CrossEntropy 很可能训不出来，通常都用 SoftIoU/Dice Loss.