Distributed Global Structure-from-Motion with a Deep Front-End

1 code implementation • 30 Nov 2023 • Ayush Baid, John Lambert, Travis Driver, Akshay Krishnan, Hayk Stepanyan, Frank Dellaert

While initial approaches to Structure-from-Motion (SfM) revolved around both global and incremental methods, most recent applications rely on incremental systems to estimate camera poses due to their superior robustness.

The Waymo Open Sim Agents Challenge

1 code implementation • NeurIPS 2023 • Nico Montali, John Lambert, Paul Mougin, Alex Kuefler, Nick Rhinehart, Michelle Li, Cole Gulino, Tristan Emrich, Zoey Yang, Shimon Whiteson, Brandyn White, Dragomir Anguelov

Simulation with realistic, interactive agents represents a key task for autonomous vehicle software development.

Autonomous Driving

Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

1 code implementation • Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 2021 • Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, Deva Ramanan, Peter Carr, James Hays

Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category.

3D Object Detection Motion Forecasting +1

Trust, but Verify: Cross-Modality Fusion for HD Map Change Detection

2 code implementations • 14 Dec 2022 • John Lambert, James Hays

High-definition (HD) map change detection is the task of determining when sensor data and map data are no longer in agreement with one another due to real-world changes.

Change Detection

MSeg: A Composite Dataset for Multi-domain Semantic Segmentation

2 code implementations • CVPR 2020 • John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun

We adopt zero-shot cross-dataset transfer as a benchmark to systematically evaluate a model's robustness and show that MSeg training yields substantially more robust models in comparison to training on individual datasets or naive mixing of datasets without the presented contributions.

Computational Efficiency Instance Segmentation +3

Adversarial Machine Learning -- Industry Perspectives

no code implementations • 4 Feb 2020 • Ram Shankar Siva Kumar, Magnus Nyström, John Lambert, Andrew Marshall, Mario Goertzel, Andi Comissoneru, Matt Swann, Sharon Xia

Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML) systems.

BIG-bench Machine Learning

Argoverse: 3D Tracking and Forecasting with Rich Maps

3 code implementations • CVPR 2019 • Ming-Fang Chang, John Lambert, Patsorn Sangkloy, Jagjeet Singh, Slawomir Bak, Andrew Hartnett, De Wang, Peter Carr, Simon Lucey, Deva Ramanan, James Hays

In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting.

3D Object Tracking Autonomous Vehicles +3

Deep Learning under Privileged Information Using Heteroscedastic Dropout

1 code implementation • CVPR 2018 • John Lambert, Ozan Sener, Silvio Savarese

This is what the Learning Under Privileged Information (LUPI) paradigm endeavors to model by utilizing extra knowledge only available during training.

Image Classification Machine Translation +1