# Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation

arXiv: https://arxiv.org/abs/2111.07971 · HTML: https://mlsanity.com/paper/2111.07971/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 62 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2007.09222/) (2020)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World](https://mlsanity.com/paper/2006.09348/) (2020)
- [Meta-Sim: Learning to Generate Synthetic Datasets](https://mlsanity.com/paper/1904.11621/) (2019)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)

## Built on by (most cited first, 12 of 12)

- [Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2303.01686/) (2023)
- [Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors](https://mlsanity.com/paper/2305.11239/) (2023)
- [LightSim: Neural Lighting Simulation for Urban Scenes](https://mlsanity.com/paper/2312.06654/) (2023)
- [Towards Viewpoint Robustness in Bird's Eye View Segmentation](https://mlsanity.com/paper/2309.05192/) (2023)
- [Deep Transfer Learning for Intelligent Vehicle Perception: a Survey](https://mlsanity.com/paper/2306.15110/) (2023)
- [Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting](https://mlsanity.com/paper/2302.04832/) (2023)
- [OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection](https://mlsanity.com/paper/2411.17761/) (2024)
- [BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection](https://mlsanity.com/paper/2211.17126/) (2022)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [Deep incremental learning models for financial temporal tabular datasets with distribution shifts](https://mlsanity.com/paper/2303.07925/) (2023)
- [BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2509.14151/) (2025)
- [Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision](https://mlsanity.com/paper/2510.25205/) (2025)

## Abstract (arXiv)

Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations. However, the domain gap between the synthetic and real data remains, raising the following important question: What are the best ways to utilize a self-driving simulator for perception tasks? In this work, we build on top of recent advances in domain-adaptation theory, and from this perspective, propose ways to minimize the reality gap. We primarily focus on the use of labels in the synthetic domain alone. Our approach introduces both a principled way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. Our method is easy to implement in practice as it is agnostic of the network architecture and the choice of the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data (cameras, lidar) using an open-source simulator (CARLA), and evaluate the entire framework on a real-world dataset (nuScenes). Last but not least, we show what types of variations (e.g. weather conditions, number of assets, map design, and color diversity) matter to perception networks when trained with driving simulators, and which ones can be compensated for with our domain adaptation technique.