Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909618153717760 |
|---|---|
| author | Katare, Dewant Noguero, David Solans Park, Souneil Kourtellis, Nicolas Janssen, Marijn Ding, Aaron Yi |
| author_facet | Katare, Dewant Noguero, David Solans Park, Souneil Kourtellis, Nicolas Janssen, Marijn Ding, Aaron Yi |
| contents | The accuracy and fairness of perception systems in autonomous driving are essential, especially for vulnerable road users such as cyclists, pedestrians, and motorcyclists who face significant risks in urban driving environments. While mainstream research primarily enhances class performance metrics, the hidden traits of bias inheritance in the AI models, class imbalances and disparities within the datasets are often overlooked. Our research addresses these issues by investigating class imbalances among vulnerable road users, with a focus on analyzing class distribution, evaluating performance, and assessing bias impact. Utilizing popular CNN models and Vision Transformers (ViTs) with the nuScenes dataset, our performance evaluation indicates detection disparities for underrepresented classes. Compared to related work, we focus on metric-specific and Cost-Sensitive learning for model optimization and bias mitigation, which includes data augmentation and resampling. Using the proposed mitigation approaches, we see improvement in IoU(\%) and NDS(\%) metrics from 71.3 to 75.6 and 80.6 to 83.7 for the CNN model. Similarly, for ViT, we observe improvement in IoU and NDS metrics from 74.9 to 79.2 and 83.8 to 87.1. This research contributes to developing reliable models while enhancing inclusiveness for minority classes in datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset Katare, Dewant Noguero, David Solans Park, Souneil Kourtellis, Nicolas Janssen, Marijn Ding, Aaron Yi Computer Vision and Pattern Recognition The accuracy and fairness of perception systems in autonomous driving are essential, especially for vulnerable road users such as cyclists, pedestrians, and motorcyclists who face significant risks in urban driving environments. While mainstream research primarily enhances class performance metrics, the hidden traits of bias inheritance in the AI models, class imbalances and disparities within the datasets are often overlooked. Our research addresses these issues by investigating class imbalances among vulnerable road users, with a focus on analyzing class distribution, evaluating performance, and assessing bias impact. Utilizing popular CNN models and Vision Transformers (ViTs) with the nuScenes dataset, our performance evaluation indicates detection disparities for underrepresented classes. Compared to related work, we focus on metric-specific and Cost-Sensitive learning for model optimization and bias mitigation, which includes data augmentation and resampling. Using the proposed mitigation approaches, we see improvement in IoU(\%) and NDS(\%) metrics from 71.3 to 75.6 and 80.6 to 83.7 for the CNN model. Similarly, for ViT, we observe improvement in IoU and NDS metrics from 74.9 to 79.2 and 83.8 to 87.1. This research contributes to developing reliable models while enhancing inclusiveness for minority classes in datasets. |
| title | Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.10397 |