ServiceNow Research

Unsupervised Learning

Reducing Noise in GAN Training with Variance Reduced Extragradient
Reducing Noise in GAN Training with Variance Reduced Extragradient
We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can …
Conference on Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite Code
Fourier-CPPNs for Image Synthesis
Fourier-CPPNs for Image Synthesis
Compositional Pattern Producing Networks (CPPNs) are differentiable networks that independently map (x, y) pixel coordinates to (r, g, …
Workshop at the International Conference on Computer Vision (ICCV),  2019.
PDF Cite Code
Adversarial Computation of Optimal Transport Maps
Adversarial Computation of Optimal Transport Maps
Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport …
ArXiv,  2019.
PDF Cite Code
Hierarchical Importance Weighted Autoencoders
Hierarchical Importance Weighted Autoencoders
Importance weighted variational inference (Burda et al., 2015) uses multiple i.i.d. samples to have a tighter variational lower bound. …
International Conference on Machine Learning (ICML),  2019.
PDF Cite Code
Adversarial Mixup Resynthesizers
Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
Workshop at the International Conference on Learning Representations (ICLR),  2019.
PDF Cite Code
Fashion-Gen: The Generative Fashion Dataset and Challenge
Fashion-Gen: The Generative Fashion Dataset and Challenge
We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by …
Women in Machine Learning (WiML),  2018.
PDF Cite Code
Unsupervised Depth Estimation, 3D Face Rotation and Replacement
Unsupervised Depth Estimation, 3D Face Rotation and Replacement
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also …
Conference on Neural Information Processing Systems (NeurIPS),  2018.
PDF Cite Code
Fashion-Gen: The Generative Fashion Dataset and Challenge
Fashion-Gen: The Generative Fashion Dataset and Challenge
We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by …
Workshop at the International Conference on Machine Learning (ICML),  2018.
PDF Cite Code
Neural Autoregressive Flows
Neural Autoregressive Flows
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, …
International Conference on Machine Learning (ICML),  2018.
PDF Cite Code
Unsupervised Domain Adaptation with Similarity Learning
Unsupervised Domain Adaptation with Similarity Learning
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an …
Computer Vision and Pattern Recognition (CVPR),  2018.
PDF Cite