Saxe et al.

other · 2 mentions across 1 reading

In this course

Saxe et al. appear as a passing reference in technical discussions of GAN architectures and training procedures, though their specific contribution is not detailed in these excerpts. The citations seem to draw on foundational work in neural network initialization and scaling strategies that underpin contemporary generative models, which are central to discussions of AI-generated imagery in the seminar's broader engagement with algorithmic aesthetics.

Mentioned in 1 reading

Andrew Brock

et al., LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS

In this section, we explore methods for scaling up GAN training to reap the performance benefits of larger models and larger batches. As a baseline, we employ the SA-GAN architecture of Zhang et al. (2018), which uses the hinge loss (Lim & …Our basic setup follows SA-GAN (Zhang et al., 2018), and is implemented in TensorFlow (Abadi et al., 2016). We employ the architectures detailed in Appendix B, with non-local blocks inserted at a single stage in each network. Both G and D n…

Appears alongside

People mentioned in the same passages — sorted by co-occurrence weight.

Zhang et al. 2 de Vries et al. 1 Dumoulin et al. 1 Glorot & Bengio 1 Karras et al. 1 Lim & Ye 1 Mescheder et al. 1 Miyato & Koyama 1 Radford et al. 1 Tran et al. 1 Yazc et al. 1 Abadi et al. 1 Ioffe & Szegedy 1 Kingma & Ba 1 Miyato et al. 1