Summary of Cross-camera Distracted Driver Classification Through Feature Disentanglement and Contrastive Learning, by Simone Bianco et al.
Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning
by Simone Bianco, Luigi Celona, Paolo Napoletano
First submitted to arxiv on: 20 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
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 paper introduces a robust neural network model called DBMNet that can accurately classify distracted drivers despite changes in camera position within the vehicle. The model is designed to withstand variations in training data conditions by incorporating a disentanglement module to discard camera view information and contrastive learning to enhance feature encoding of various driver actions. The authors validate their approach on the 100-Driver dataset, achieving an average increment of 9% in Top-1 accuracy compared to state-of-the-art methods. Additionally, the model demonstrates superior generalization capabilities across three benchmark datasets: AUCDD-V1, EZZ2021, and SFD. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create safer driving by developing a smart system that can accurately identify distracted drivers. The researchers created a special kind of artificial intelligence called DBMNet that is very good at recognizing when drivers are not paying attention to the road. They tested their model on lots of different camera views and found it worked well, even when the camera was positioned differently than during training. This means the system can be used in real-life driving situations. |
Keywords
» Artificial intelligence » Attention » Generalization » Neural network
