DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection
In: 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press, 2022. URL https://bmvc2022.mpi-inf.mpg.de/0916.pdf; (2022)
Online
report
Deep learning has achieved notable success in 3D object detection with the advent of large-scale point cloud datasets. However, severe performance degradation in the past trained classes, i.e., catastrophic forgetting, still remains a critical issue for real-world deployment when the number of classes is unknown or may vary. Moreover, existing 3D class-incremental detection methods are developed for the single-domain scenario, which fail when encountering domain shift caused by different datasets, varying environments, etc. In this paper, we identify the unexplored yet valuable scenario, i.e., class-incremental learning under domain shift, and propose a novel 3D domain adaptive class-incremental object detection framework, DA-CIL, in which we design a novel dual-domain copy-paste augmentation method to construct multiple augmented domains for diversifying training distributions, thereby facilitating gradual domain adaptation. Then, multi-level consistency is explored to facilitate dual-teacher knowledge distillation from different domains for domain adaptive class-incremental learning. Extensive experiments on various datasets demonstrate the effectiveness of the proposed method over baselines in the domain adaptive class-incremental learning scenario.
Comment: Accepted by the 33rd British Machine Vision Conference (BMVC 2022)
Titel: |
DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection
|
---|---|
Autor/in / Beteiligte Person: | Zhao, Ziyuan ; Xu, Mingxi ; Qian, Peisheng ; Pahwa, Ramanpreet Singh ; Chang, Richard |
Link: | |
Quelle: | 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press, 2022. URL https://bmvc2022.mpi-inf.mpg.de/0916.pdf; (2022) |
Veröffentlichung: | 2022 |
Medientyp: | report |
Schlagwort: |
|
Sonstiges: |
|