Thanks for the fantastic post. I have a question on the Loss Recovered comparison. In the text, you calculate the ratio L−LcleanLGSAE−Lclean. Based on the interpretation, it seems that a higher ratio is better. However, it seems to me that if the domain-specific SAE is good enough and perfectly reconstructed, we should have L=Lclean. In this case, the ratio from the above definition is zero, while this seems to be an optimal case. Can you point out where my interpretation may be wrong?
Thanks for the fantastic post. I have a question on the Loss Recovered comparison. In the text, you calculate the ratio L−LcleanLGSAE−Lclean. Based on the interpretation, it seems that a higher ratio is better. However, it seems to me that if the domain-specific SAE is good enough and perfectly reconstructed, we should have L=Lclean. In this case, the ratio from the above definition is zero, while this seems to be an optimal case. Can you point out where my interpretation may be wrong?
Oops, good spot! I meant to write 1 minus that quantity. I’ve edited the OP.