ServiceNow AI Research

9

Objects of violence: synthetic data for practical ML in human rights investigations
Objects of violence: synthetic data for practical ML in human rights investigations
We introduce a machine learning workflow to search for, identify, and meaningfully triage videos and images of munitions, weapons, and …
Workshop at the Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite
Retrieving Signals in the Frequency Domain with Deep Complex Extractors
Retrieving Signals in the Frequency Domain with Deep Complex Extractors
Recent advances have made it possible to create deep complex-valued neural networks. Despite this progress, the potential power of …
Workshop at the Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite
Tackling Climate Change with Machine Learning
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here …
Workshop at the Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation
We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time. CBS achieves …
Workshop at the International Conference on Computer Vision (ICCV),  2019.
PDF Cite
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
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and …
Workshop at the International Conference on Machine Learning (ICML),  2019.
PDF Cite
Learning Global Variations in Outdoor PM_2.5 Concentrations with Satellite Images
Here we present a new method of estimating global variations in outdoor PM2.5 concentrations using satellite images combined with …
Workshop at the International Conference on Machine Learning (ICML),  2019.
PDF Cite
Stochastic Neural Network with Kronecker Flow
Stochastic Neural Network with Kronecker Flow
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their …
Workshop at the International Conference on Machine Learning (ICML),  2019.
PDF Cite
Adaptive Cross-Modal Few-shot Learning
Adaptive Cross-Modal Few-shot Learning
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to …
Workshop at the International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Adaptive Masked Weight Imprinting for Few-Shot Segmentation
Adaptive Masked Weight Imprinting for Few-Shot Segmentation
Deep learning has mainly thrived by training on large-scale datasets. However, for continual learning in applications such as robotics, …
Workshop at the International Conference on Learning Representations (ICLR),  2019.
PDF Cite