Brain2GAN: Feature-disentangled neural encoding and decoding of visual perception in the primate brain.

For faces, the comparison between w -based and VGGFace-1-based encoders shows no significant difference (2-Sample T-Test; t (1918) = −0.2859, p = 0.78) but we found highly significant differences when comparing w -based encoders with VGGFace-3 (2-Sample T-Test; t (1918) = 16.5817, p = 8.21 e − 58) and with VGGFace-5 (2-Sample T-Test; t (1918) = 15.0820, p = 1.17 e − 48).

also in 60,174 other papers