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 enabled training of much deeper neural networks. In the course readings, He's ResNet-50 appears as a feature extractor for evaluating generative model outputs, allowing researchers to compare generated images against real data in learned feature space rather than pixel space. His architectural innovations underpin the infrastructure that modern generative models like BigGAN build upon, making ResNet a standard tool for assessing whether AI-generated content learns meaningful representations aligned with human perception.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.