Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5490-5498
DOI: 10.1609/aaai.v38i6.28358 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Kewei Wang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref).
Abstract (Originalsprache)
Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and re-generates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://github.com/kwwcv/SSMP.
Zitieren
APA
Wang, K., Wu, Y., Pan, Z., Li, X., Xian, K., Wang, Z., Cao, Z., & Lin, G. (2024). Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5490-5498. https://doi.org/10.1609/aaai.v38i6.28358
Vancouver
Wang K, Wu Y, Pan Z, Li X, Xian K, Wang Z, et al. Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5490-5498. doi:10.1609/aaai.v38i6.28358
BibTeX
@article{Wang2024,
author = {Wang, Kewei and Wu, Yizheng and Pan, Zhiyu and Li, Xingyi and Xian, Ke and Wang, Zhe and Cao, Zhiguo and Lin, Guosheng},
title = {Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5490--5498},
doi = {10.1609/aaai.v38i6.28358}
}
EUVIMED