CNN only learning the mean of targets

I’m dealing with a regression task by training a CNN with 334x334 satellite images. As I mentioned in my previous posts, I use MSE loss along with Adam optimizer, and the loss fails to converge. I now realize the reason why the loss fails to converge is that it only learns the mean of the targets. For example, if I feed it with 100 data points with mean of target = 7, then all its predictions will be very close to 7 (as shown in the picture below, where x-axis is the true value, and y-axis is the predicted value):

One of my guesses in this case it that my CNN does not learn any visual structures from the image, so I try different architectures such as ResNet and AlexNet, but the problem still exists. How can I prevent my network from this behavior?

I had a similar issue when training a CNN for regression of numerical data.
I decreased my learning rate and my problem is solved.
Also check that your dataset is balanced.

1 Like

I tried creating a simple regression model using Pytorch. The weights are converging to 0 and the bias to mean in the parameters hence all predictions are close to the mean. I tried decreasing the learning rate as well but still not able to converge.