ai老师人工智能培训老师计算机视觉老师叶梓：计算机视觉领域的自监督学习模型——MAE-12

接上一篇

P26P27

MAE的Reconstruction target

n Our MAE reconstructs the input by predicting the pixel values for each masked patch .

n Each element in the decoder’s output is a vector of pixel values representing a patch .

n The last layer of the decoder is a linear projection whose number of output channels equals the number of pixel values in a patch.

n The decoder’s output is reshaped to form a reconstructed image.

n Our loss function computes the mean squared error (MSE) between the reconstructed and original images in the pixel space .

n We compute the loss only on masked patches , similar to BERT

 

 实验效果-Mask比例的影响

从上图可以看出，随着输入图像被遮住的比例升高，MAE的性能迅速上升，在75%左右达到最佳效果。

---

以上为叶梓老师上课讲义，供有基础的朋友或者同行使用，未完，下一篇继续……