Summary of Sustechgan: Image Generation For Object Detection in Adverse Conditions Of Autonomous Driving, by Gongjin Lan et al.
SUSTechGAN: Image Generation for Object Detection in Adverse Conditions of Autonomous Driving
by Gongjin Lan, Yang Peng, Qi Hao, Chengzhong Xu
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed SUSTechGAN framework uses customized dual attention modules, multi-scale generators, and a novel loss function to generate driving images for improving object detection of autonomous driving in adverse conditions. The framework is tested against well-known GANs and found to significantly improve the performance of retrained YOLOv5 models in rain and night conditions. The SUSTechGAN generates high-quality driving images that can be used to augment training datasets and enhance the accuracy of object detection algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SUSTechGAN is a new way to generate pictures for self-driving cars to work better in bad weather or at night. Right now, it’s hard to get the right data to train these systems because they need lots of images from difficult conditions. The SUSTechGAN team came up with a special algorithm that can make these images and use them to improve object detection in autonomous vehicles. They tested their idea and found that it works better than other methods for generating driving images. |
Keywords
» Artificial intelligence » Attention » Loss function » Object detection
