Published as a conference paper at ICLR 2019
Caption: Figure 11: Nearest neighbors in ResNet-50-avgpool (He et al., 2016) feature space. The generated image is in the top left.
Caption: Figure 12: Nearest neighbors in pixel space. The gener…The BigGAN-deep model (Figure 16) differs from BigGAN in several aspects. It uses a simpler variant of skip-$z$ conditioning: instead of first splitting $z$ into chunks, we concatenate the entire $z$ with the class embedding, and pass the r…
Kaiming He
scientist · 2 mentions across 1 reading
In this course
Kaiming He is a computer vision researcher best known for developing ResNet (Residual Networks), a foundational deep learning architecture that enables training of very deep neural networks. In these course readings, ResNet-50 appears as a feature extraction backbone used to evaluate generative model outputs, showing how discriminative architectures trained on ImageNet have become standard tools for assessing what generative systems learn and produce. His work exemplifies how advances in supervised learning directly enable and constrain the technical possibilities of generative models like BigGAN.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.