I am confused about the training part in AttnGan.

If you observe page 3. There are two types of losses for generator network: one involving the Deep Attentional Multimodal Similarity Model (DAMSM) loss $(L_{DAMSM})$ and the others for individual generator $(L_{G_i})$ for $i= 1, 2, 3$.

My doubt is: if each generator has its own loss function that is useful in training, what is the purpose in using $L_G$, i.e., with DAMSM loss function? Is my assumption wrong?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.