# What does the adversarial loss in a GAN represent?

I'm working on Pix2Pix an image-to-image translation GAN, and I noticed that there is an adversarial loss implemented using BCE, and a L1 loss implemented using MAE. I know L1 loss represents the difference between the predicted image and actual image, but I am not sure what does the GAN adversarial loss represent?

This is the official definition The adversarial loss influences whether the generator model can output images that are plausible in the target domain but the meaning is tough to understand. Is it representing the difference between the predicted probability distribution and actual probability distribution?

## 1 Answer

The adversarial loss in a GAN represents the amount of information that the generator is able to trick the discriminator into believing is true.

"The adversarial loss influences whether the generator model can output images that are plausible in the target domain"$$\rightarrow$$ means that the generator model should output images that look like they could plausibly belong to the target domain. This is important because if the generated images look too fake, it will be difficult for the discriminator to learn to correctly classify them. It's the data that determines whether and how it improves.

In addition, the adversarial loss is based on the generator model's experience of its successes and failures in the data.

• "if the generated images look too fake, it will be difficult for the discriminator to learn to correctly classify them" -> in that case wouldn't it be easy to classify them as fake? Nov 21, 2022 at 8:34
• The adversarial loss in a GAN represents the difference between the predicted probability distribution (produced by the discriminator) and the actual probability distribution (i.e., the distribution of real samples in the target domain). It is used to train the discriminator to correctly classify generated images as fake. If the generated images look too fake, it will be easy for the discriminator to classify them as fake, resulting in a high adversarial loss. This loss is used to improve the discriminator's ability to distinguish real from fake images. Dec 19, 2022 at 15:13