FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6189-6197
DOI: 10.1609/aaai.v38i6.28436 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zizhang Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref).
Abstract (Originalsprache)
Monocular 3D object detection usually adopts direct or hierarchical label supervision. Recently, the distillation supervision transfers the spatial knowledge from LiDAR- or stereo-based teacher networks to monocular detectors, but remaining the domain gap. To mitigate this issue and pursue adequate label manipulation, we exploit Foreground Depth map for feature-supervised monocular 3D object detection named FD3D, which develops the high-quality instructive intermediate features to conduct desirable auxiliary feature supervision with only the original image and annotation foreground object-wise depth map (AFOD) as input. Furthermore, we build up our instructive feature generation network to create instructive spatial features based on the sufficient correlation between image features and pre-processed AFOD, where AFOD provides the attention focus only on foreground objects to achieve clearer guidance in the detection task. Moreover, we apply the auxiliary feature supervision from the pixel and distribution level to achieve comprehensive spatial knowledge guidance. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both the KITTI and nuScenes datasets, with no external data and no extra inference computational cost. We also conduct quantitative and qualitative studies to reveal the effectiveness of our designs.
Zitieren
APA
Wu, Z., Gan, Y., Wu, Y., Wang, R., Wang, X., & Pu, J. (2024). FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6189-6197. https://doi.org/10.1609/aaai.v38i6.28436
Vancouver
Wu Z, Gan Y, Wu Y, Wang R, Wang X, Pu J. FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6189-6197. doi:10.1609/aaai.v38i6.28436
BibTeX
@article{Wu2024,
author = {Wu, Zizhang and Gan, Yuanzhu and Wu, Yunzhe and Wang, Ruihao and Wang, Xiaoquan and Pu, Jian},
title = {FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6189--6197},
doi = {10.1609/aaai.v38i6.28436}
}
EUVIMED