Skip to footer

Graph HyperNetworks for Neural Architecture Search

C. Zhang, M. Ren, R. Urtasun
Neural architecture search (NAS) automatically finds the best task-specific neural network topology, outperforming many manual architecture designs. However, it can be prohibitively expensive as the search requires training thousands of different networks, while each can last for hours. In this work, we propose the Graph HyperNetwork (GHN) to amortize the search cost: given an architecture, it directly generates the weights by running inference on a graph neural network. […] [PDF]
Meta Learning workshop @ Neural Information Processing Systems (NeurIPS), 2018

Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

F. Chou, T.-H. Lin, H. Cui, V. Radosavljevic, T. Nguyen, T. Huang, M. Niedoba, J. Schneider, N. Djuric
Following detection and tracking of traffic actors, prediction of their future motion is the next critical component of a self-driving vehicle (SDV), allowing the SDV to move safely and efficiently in its environment. This is particularly important when it comes to vulnerable road users (VRUs), such as pedestrians and bicyclists. We present a deep learning method for predicting VRU movement where we rasterize high-definition maps and actor’s surroundings into bird’s-eye view image used as input to convolutional networks. […] [PDF]
MLITS workshop @ Neural Information Processing Systems (NeurIPS), 2018

Rotated Rectangles for Symbolized Building Footprint Extraction

M. Dickenson, L. Gueguen
Building footprints (BFP) provide useful visual context for users of digital maps when navigating in space. This paper proposes a method for extracting and symbolizing building footprints from satellite imagery using a convolutional neural network (CNN). […] [PDF]
Conference on Computer Vision and Pattern Recognition (CVPR), 2018

An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

F. Such, V. Madhavan, R. Liu, R. Wang, P. Castro, Y. Li, L. Schubert, M. Bellemare, J. Clune, J. Lehman
Much human and computational effort has aimed to improve how deep reinforcement learning algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned by such methods, and investigating and comparing the representations learned by different families of reinforcement learning (RL) algorithms. […] [PDF]

Faster Neural Networks Straight from JPEG

L. Gueguen, A. Sergeev, B. Kadlec, R. Liu, J. Yosinski
The simple, elegant approach of training convolutional neural networks (CNNs) directly from RGB pixels has enjoyed overwhelming empirical success. But can more performance be squeezed out of networks by using different input representations? In this paper we propose and explore a simple idea: train CNNs directly on the blockwise discrete cosine transform (DCT) coefficients computed and available in the middle of the JPEG codec. […] [PDF]
Advances in Neural Information Processing Systems (NeurIPS), 2018

Profiling Android Applications with Nanoscope

L. Liu, L. Takamine, A. Welc
User-level tooling support for profiling Java applications executing on modern JVMs for desktop and server is quite mature – from Open JDK’s Java Flight Recorder enabling low-overhead CPU and heap profiling, through third-party async profilers (e.g. async-profiler, honest-profiler), to Open JDK’s support for low-overhead tracking of allocation call sites. […] [PDF]
Virtual Machines and Language Implementations (VMIL), 2018

Joint Mapping and Calibration via Differentiable Sensor Fusion

J. Chen, F. Obermeyer, V. Lyapunov, L. Gueguen, N. Goodman
We leverage automatic differentiation (AD) and probabilistic programming to develop an end-to-end optimization algorithm for batch triangulation of a large number of unknown objects. Given noisy detections extracted from noisily geo-located street level imagery without depth information, we jointly estimate the number and location of objects of different types, together with parameters for sensor noise characteristics and prior distribution of objects conditioned on side information. […] [PDF]
Computing Research Repository (CoRR), 2018

Learning to Localize Using a LiDAR Intensity Map

I. Bârsan, S. Wang, A. Pokrovsky, R. Urtasun
In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. […] [PDF]
Conference on Robot Learning (CORL), 2018

Deep Multi-Sensor Lane Detection

M. Bai, G. Mattyus, N. Homayounfar, S. Wang, S. K. Lakshmikanth, R. Urtasun
Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we argue that accurate image estimates do not translate to precise 3D lane boundaries, which are the input required by modern motion planning algorithms. […] [PDF]
International Conference on Intelligent Robots and Systems (IROS), 2018

HDNET: Exploiting HD Maps for 3D Object Detection

B. Yang, M. Liang, R. Urtasun
In this paper we show that High-Definition (HD) maps provide strong priors that can boost the performance and robustness of modern 3D object detectors. Towards this goal, we design a single stage detector that extracts geometric and semantic features from the HD maps. […] [PDF]
Conference on Robot Learning (CORL), 2018

Probabilistic Meta-Representations Of Neural Networks

T. Karaletsos, P. Dayan, Z. Ghahramani
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently. Here, we consider a richer prior distribution in which units in the network are represented by latent variables, and the weights between units are drawn conditionally on the values of the collection of those variables. […] [PDF]
UAI 2018 Uncertainty In Deep Learning Workshop (UDL), 2018

Pyro: Deep Universal Probabilistic Programming

E. Bingham, J. Chen, M. Jankowiak, F. Obermeyer, N. Pradhan, T. Karaletsos, R. Singh, P. Szerlip, P. Horsfall, N. Goodman
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. […] [PDF]
Journal of Machine Learning Research (JMLR), 2018

IntentNet: Learning to Predict Intention from Raw Sensor Data

S. Casas, W. Luo, R. Urtasun
In order to plan a safe maneuver, self-driving vehicles need to understand the intent of other traffic participants. We define intent as a combination of discrete high level behaviors as well as continuous trajectories describing future motion. In this paper we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment. […] [PDF]
Conference on Robot Learning (CORL), 2018

Dynamic Pricing and Matching in Ride-Hailing Platforms

N. Korolko, D. Woodard, C. Yan, H. Zhu
Ride-hailing platforms such as Uber, Lyft and DiDi have achieved explosive growth and reshaped urban transportation. The theory and technologies behind these platforms have become one of the most active research areas in the fields of economics, operations research, computer science, and transportation engineering. […] [PDF]

The Perfect uberPOOL: A Case Study on Trade-Offs

J. Lo, S. Morseman
Case Study—One of Uber’s company missions is to make carpooling more affordable and reliable for riders, and effortless for drivers. In 2014 the company launched uberPOOL to make it easy for riders to share their trip with others heading in the same direction. Fundamental to the mechanics of uberPOOL is the intelligence that matches riders for a trip, which can introduce various uncertainties into the user experience. […]
Ethnographic Praxis in Industry Conference (EPIC), 2018

Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds

C. Zhang, W. Luo, R. Urtasun
We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets have been annotated. […] [PDF]
International Conference on 3D Vision (3DV), 2018

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

M. Liang, B. Yang, S. WangR. Urtasun
In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDAR feature maps at different levels of resolution. […] [PDF]
European Conference on Computer Vision (ECCV), 2018

Single Image Intrinsic Decomposition Without a Single Intrinsic Image

W. Ma, H, Chu, B. Zhou, R. Urtasun, A. Torralba
We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets have been annotated. […] [PDF]
European Conference on Computer Vision (ECCV), 2018

Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks

H. Cui, V. Radosavljevic, F. Chou, T.-H. Lin, T. Nguyen, T. Huang, J. Schneider, N. Djuric
Autonomous driving presents one of the largest problems that the robotics and artificial intelligence communities are facing at the moment, both in terms of difficulty and potential societal impact. Self-driving vehicles (SDVs) are expected to prevent road accidents and save millions of lives while improving the livelihood and life quality of many more. […] [PDF]
International Conference on Robotics and Automation (ICRA), 2019

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

T. Miconi, A. Rawal, J. Clune, K. Stanley
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma’s Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to improve performance on hard-exploration domains. To address this shortfall, we introduce a new algorithm called Go-Explore. […] [PDF]
International Conference on Learning Representations (ICLR), 2019

LSQ++: lower running time and higher recall in multi-codebook quantization

J. Martinez, S. Zakhmi, H. Hoos, and J. Little
Multi-codebook quantization (MCQ) is the task of expressing a set of vectors as accurately as possible in terms of discrete entries in multiple bases. Work in MCQ is heavily focused on lowering quantization error, thereby improving distance estimation and recall on benchmarks of visual descriptors at a fixed memory budget. […] [PDF]
European Conference on Computer Vision (ECCV), 2018

End-to-End Deep Structured Models for Drawing Crosswalks

J. Liang, R. Urtasun
In this paper we address the problem of detecting crosswalks from LiDAR and camera imagery. Towards this goal, given multiple Li-DAR sweeps and the corresponding imagery, we project both inputs onto the ground surface to produce a top down view of the scene. […] [PDF]
European Conference on Computer Vision (ECCV), 2018

Functional Programming for Modular Bayesian Inference

A. Ścibior, O. Kammar, Z. Ghahramani

We present an architectural design of a library for Bayesian modelling and inference in modern functional programming languages. The novel aspect of our approach are modular implementations of existing state-ofthe-art inference algorithms. Our design relies on three inherently functional features: higher-order functions, inductive data-types, and support for either type-classes or an expressive module system. […] [PDF]

Safe stream-based programming with refinement types

B. Stein, L. Clapp, M. Sridharan, B.-Y. E. Chang
A type-based approach that can statically prove the thread-safety of UI accesses in stream-based software. We implement the system as an annotation-based Java typechecker for Android programs built upon the popular ReactiveX. We evaluate on 8 open-source apps and report on our experience applying the typechecker to two much larger apps from the Uber. […] [PDF]
IEEE/ACM International Conference on Automated Software Engineering (ASE), 2018

Labor Market Equilibration: Evidence from Uber

J. Hall, J. Horton, D. Knoepfle
Using a city-week panel of US ride-sharing markets created by Uber, we estimate the effects of sudden fare changes on market outcomes, focusing on the supply-side. […] [PDF]

Safely and Quickly Deploying New Features with a Staged Rollout Framework Using Sequential Test and Adaptive Experimental Design

Z. Zhao, M. Liu, A. Deb
During the rapid development cycle for Internet products (websites and mobile apps), new features are developed and rolled out to users constantly. Features with code defects or design flaws can cause outages and significant degradation of user experience. The traditional method of code review and change management can be time-consuming and error-prone. In order to make the feature rollout process safe and fast, this paper proposes a methodology for rolling out features in an automated way using an adaptive experimental design. […] [PDF]
International Conference on Computational Intelligence and Applications, (ICCIA), 2018

Uber Happy? Work and Well-being in the “Gig Economy”

T. Berger, C. B. Frey, G. Levin, S. R. Danda
We explore the rise of the so-called “gig economy” through the lens of Uber and its drivers in the United Kingdom. Using administrative data from Uber and a new representative survey of London drivers, we explore their backgrounds, earnings, and well being. […] [PDF]
The 68th Panel Meeting of Economic Policy, 2019

Differentiable Compositional Kernel Learning for Gaussian Processes

S. Sun, G. Zhang, C. Wang, W. Zeng, J. Li, R. Grosse
The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexible family of kernels represented by a neural network. […] [PDF]
International Conference on Machine Learning (ICML), 2018

Discovering Interpretable Representations for Both Deep Generative and Discriminative Models

T. Adel, Z. Ghahramani, A. Weller
Interpretability of representations in both deep generative and discriminative models is highly desirable. Current methods jointly optimize an objective combining accuracy and interpretability. However, this may reduce accuracy, and is not applicable to already trained models. We propose two interpretability frameworks. First, we provide an interpretable lens for an existing model. We use a generative model which takes as input the representation in an existing (generative or discriminative) model, weakly supervised by limited side information. […] [PDF]
International Conference on Machine Learning (ICML), 2018

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

M. Teichmann, M. Weber, M. Zöllner, R. Cipolla, R. Urtasun
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. […] [PDF]
IEEE Intelligent Vehicles Symposium (IV), 2018

Page 3 of 6