问题描述
当人们尝试使用CNN解决语义分割的任务时，他们通常在训练过程中使用softmax-crossentropy损失(请参阅完全转换-Long ).但是，在比较不同方法的性能时，报告了诸如交叉路口交叉连接之类的措施.
When people try to solve the task of semantic segmentation with CNN's they usually use a softmax-crossentropy loss during training (see Fully conv. - Long). But when it comes to comparing the performance of different approaches measures like intersection-over-union are reported.
我的问题是，为什么人们不直接培训他们想要优化的指标?对于我来说，在训练过程中进行某种程度的训练似乎很奇怪，但是对基准进行另一种评估却很容易.
My question is why don't people train directly on the measure they want to optimize? Seems odd to me to train on some measure during training, but evaluate on another measure for benchmarks.
我可以看到，IOU在没有类的情况下训练样本存在问题(联合= 0和交集= 0 =>除以零).但是，当我可以确保我的每个基本事实样本都包含所有类别时，还有其他理由不使用此度量标准吗?
I can see that the IOU has problems for training samples, where the class is not present (union=0 and intersection=0 => division zero by zero). But when I can ensure that every sample of my ground truth contains all classes, is there another reason for not using this measure?
推荐答案
检出此纸张其中他们提出了一种使IoU概念与众不同的方法.我实施了他们的解决方案，并取得了惊人的成绩！
Checkout this paper where they come up with a way to make the concept of IoU differentiable. I implemented their solution with amazing results!
这篇关于为什么不使用IOU进行培训?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！