Study of Dropout in PointPillars with 3D Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914932044333056 |
|---|---|
| author | Sun, Xiaoxiang Fox, Geoffrey |
| author_facet | Sun, Xiaoxiang Fox, Geoffrey |
| contents | 3D object detection is critical for autonomous driving, leveraging deep learning techniques to interpret LiDAR data. The PointPillars architecture is a prominent model in this field, distinguished by its efficient use of LiDAR data. This study provides an analysis of enhancing the performance of PointPillars model under various dropout rates to address overfitting and improve model generalization. Dropout, a regularization technique, involves randomly omitting neurons during training, compelling the network to learn robust and diverse features. We systematically compare the effects of different enhancement techniques on the model's regression performance during training and its accuracy, measured by Average Precision (AP) and Average Orientation Similarity (AOS). Our findings offer insights into the optimal enhancements, contributing to improved 3D object detection in autonomous driving applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Study of Dropout in PointPillars with 3D Object Detection Sun, Xiaoxiang Fox, Geoffrey Computer Vision and Pattern Recognition Machine Learning 3D object detection is critical for autonomous driving, leveraging deep learning techniques to interpret LiDAR data. The PointPillars architecture is a prominent model in this field, distinguished by its efficient use of LiDAR data. This study provides an analysis of enhancing the performance of PointPillars model under various dropout rates to address overfitting and improve model generalization. Dropout, a regularization technique, involves randomly omitting neurons during training, compelling the network to learn robust and diverse features. We systematically compare the effects of different enhancement techniques on the model's regression performance during training and its accuracy, measured by Average Precision (AP) and Average Orientation Similarity (AOS). Our findings offer insights into the optimal enhancements, contributing to improved 3D object detection in autonomous driving applications. |
| title | Study of Dropout in PointPillars with 3D Object Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.00673 |