Stat.ML Papers@StatMLPapersData Redaction from Pre-trained GANs. (arXiv:2206.14389v3 [cs.LG] UPDATED)arxiv.orgData Redaction from Pre-trained GANsLarge pre-trained generative models are known to occasionally output undesirable samples, which undermines their trustworthiness. The common way to mitigate this is to re-train them differently...2:45 AM · Jan 19, 2023·551 Views
