Charbonnier loss
时间: 2024-05-28 22:13:31 浏览: 24
Charbonnier loss, also known as L1-Squared loss or pseudo-Huber loss, is a smooth approximation of the L1 loss function. It is commonly used in image processing and computer vision tasks for its ability to preserve edges while still being differentiable.
The Charbonnier loss function is defined as:
L(x,y) = (1/2) * (x - y)^2 / (c^2 + (x - y)^2)
where x and y are the predicted and target values, and c is a hyperparameter that controls the sensitivity of the loss to differences between x and y. When c is small, the loss is similar to the L1 loss, and when c is large, it approaches the L2 loss.
The Charbonnier loss function is particularly useful for tasks such as image denoising, deblurring, and super-resolution, where preserving sharp edges is important.
相关推荐
![doc](https://img-home.csdnimg.cn/images/20210720083327.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![xlsx](https://img-home.csdnimg.cn/images/20210720083732.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![pptx](https://img-home.csdnimg.cn/images/20210720083543.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![xlsx](https://img-home.csdnimg.cn/images/20210720083732.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)