Xie Saining’s Team Releases Second-Generation Representation Autoencoder RAEv2
刚刚,谢赛宁团队放出第二代表征自编码器
Xie Saining’s team, Adobe Research, and the Australian National University released RAEv2, which reaches gFID 1.06 after 80 epochs on ImageNet-256 and reduces EPFID@2 from 177 epochs to 35 epochs while keeping compute at 189 GFLOPs.
Why it matters: Xie Saining's team with Adobe Research and ANU released RAEv2, cutting ImageNet-256 convergence from 177 epochs to 35 while holding compute at 189 GFLOPs.