722 citations · 2k across the 48 of their papers we have counts for
16 papers · 1 filter
LID 2020: The Learning from Imperfect Data Challenge Results
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…
Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Yuxuan Zhang, Wenzheng Chen, Huan Ling +4
Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high…
Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
Jonas Wulff, Antonio Torralba
Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been s…
Understanding the Role of Individual Units in a Deep Neural Network
David Bau, Jun-Yan Zhu, Hendrik Strobelt +3
Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In thi…
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
William Peebles, John Peebles, Jun-Yan Zhu +2
Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a sim…
Detecting natural disasters, damage, and incidents in the wild
Ethan Weber, Nuria Marzo, Dim P. Papadopoulos +5
Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious task performed by on-the-ground emergency responders and analysts. Social media has emer…