Guardado en:
Detalles Bibliográficos
Autores principales: Kumar, Abhinav, Guo, Yuliang, Huang, Xinyu, Ren, Liu, Liu, Xiaoming
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2403.20318
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909154977775616
author Kumar, Abhinav
Guo, Yuliang
Huang, Xinyu
Ren, Liu
Liu, Xiaoming
author_facet Kumar, Abhinav
Guo, Yuliang
Huang, Xinyu
Ren, Liu
Liu, Xiaoming
contents Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird
format Preprint
id arxiv_https___arxiv_org_abs_2403_20318
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
Kumar, Abhinav
Guo, Yuliang
Huang, Xinyu
Ren, Liu
Liu, Xiaoming
Computer Vision and Pattern Recognition
Artificial Intelligence
Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird
title SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2403.20318