# Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing

arXiv: https://arxiv.org/abs/2201.03246 · HTML: https://mlsanity.com/paper/2201.03246/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)
- [Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfer](https://mlsanity.com/paper/1803.03341/) (2018)
- [SoilingNet: Soiling Detection on Automotive Surround-View Cameras](https://mlsanity.com/paper/1905.01492/) (2019)
- [YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles](https://mlsanity.com/paper/2112.11798/) (2021)
- [Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions](https://mlsanity.com/paper/2007.13971/) (2020)
- [Worsening Perception: Real-time Degradation of Autonomous Vehicle Perception Performance for Simulation of Adverse Weather Conditions](https://mlsanity.com/paper/2103.02760/) (2021)
- [Template Matching Advances and Applications in Image Analysis](https://mlsanity.com/paper/1610.07231/) (2016)
- [Explorations and Lessons Learned in Building an Autonomous Formula SAE Car from Simulations](https://mlsanity.com/paper/1905.05940/) (2019)
- [Real-time 3D Traffic Cone Detection for Autonomous Driving](https://mlsanity.com/paper/1902.02394/) (2019)
- [Rainy screens: Collecting rainy datasets, indoors](https://mlsanity.com/paper/2003.04742/) (2020)
- [Autonomous Driving System Design for Formula Student Driverless Racecar](https://mlsanity.com/paper/1809.07636/) (2018)
- [Real-time Streaming Perception System for Autonomous Driving](https://mlsanity.com/paper/2107.14388/) (2021)

## Built on by (most cited first, 3 of 3)

- [Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions](https://mlsanity.com/paper/2306.13290/) (2023)
- [Extrapolated Urban View Synthesis Benchmark](https://mlsanity.com/paper/2412.05256/) (2024)
- [Style-Based Neural Architectures for Real-Time Weather Classification](https://mlsanity.com/paper/2604.18251/) (2026)

## Abstract (arXiv)

In an autonomous driving system, perception - identification of features and objects from the environment - is crucial. In autonomous racing, high speeds and small margins demand rapid and accurate detection systems. During the race, the weather can change abruptly, causing significant degradation in perception, resulting in ineffective manoeuvres. In order to improve detection in adverse weather, deep-learning-based models typically require extensive datasets captured in such conditions - the collection of which is a tedious, laborious, and costly process. However, recent developments in CycleGAN architectures allow the synthesis of highly realistic scenes in multiple weather conditions. To this end, we introduce an approach of using synthesised adverse condition datasets in autonomous racing (generated using CycleGAN) to improve the performance of four out of five state-of-the-art detectors by an average of 42.7 and 4.4 mAP percentage points in the presence of night-time conditions and droplets, respectively. Furthermore, we present a comparative analysis of five object detectors - identifying the optimal pairing of detector and training data for use during autonomous racing in challenging conditions.