# Improving Image Data Leakage Detection in Automotive Software

arXiv: https://arxiv.org/abs/2410.23312 · HTML: https://mlsanity.com/paper/2410.23312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Builds on (most cited first, 12 of 12)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation](https://mlsanity.com/paper/1904.07773/) (2019)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline](https://mlsanity.com/paper/2012.02124/) (2020)
- [A Critical Study on Data Leakage in Recommender System Offline Evaluation](https://mlsanity.com/paper/2010.11060/) (2020)
- [Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning](https://mlsanity.com/paper/2401.13796/) (2024)
- [Cirrus: A Long-range Bi-pattern LiDAR Dataset](https://mlsanity.com/paper/2012.02938/) (2020)
- [Data Leakage in Notebooks: Static Detection and Better Processes](https://mlsanity.com/paper/2209.03345/) (2022)
- [Critical analysis on the reproducibility of visual quality assessment using deep features](https://mlsanity.com/paper/2009.05369/) (2020)
- [Abstract Interpretation-Based Data Leakage Static Analysis](https://mlsanity.com/paper/2211.16073/) (2022)

## Abstract (arXiv)

Data leakage is a very common problem that is often overlooked during splitting data into train and test sets before training any ML/DL model. The model performance gets artificially inflated with the presence of data leakage during the evaluation phase which often leads the model to erroneous prediction on real-time deployment. However, detecting the presence of such leakage is challenging, particularly in the object detection context of perception systems where the model needs to be supplied with image data for training. In this study, we conduct a computational experiment on the Cirrus dataset from our industrial partner Volvo Cars to develop a method for detecting data leakage. We then evaluate the method on another public dataset, Kitti, which is a popular and widely accepted benchmark dataset in the automotive domain. The results show that thanks to our proposed method we are able to detect data leakage in the Kitti dataset, which was previously unknown.