Metraipolis › archive › dc_bc83f0e6b76f

CL3DOD: Understanding the Stability-Plasticity Dilemma in Outdoor Class-Incremental 3D Object Detection — arXiv:2611.03229

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03229
License (as archived)
CC0-1.0
Archived
2026-11-03T11:42:51.025Z
SHA-256 of the archived text
5cd63251c54992911cadf55d21292c176f3e82b31026e4d99d361c15f93871d7
Stable URL of this page
https://metraipolis.com/documento/dc_bc83f0e6b76f

How to cite

CL3DOD: Understanding the Stability-Plasticity Dilemma in Outdoor Class-Incremental 3D Object Detection — arXiv:2611.03229 — arXiv (en), https://arxiv.org/abs/2611.03229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc83f0e6b76f (Metraipolis archive dc_bc83f0e6b76f, sha256 5cd63251c54992911cadf55d21292c176f3e82b31026e4d99d361c15f93871d7)
BibTeX
@misc{dcbc83f0e6b76f,
  title = {CL3DOD: Understanding the Stability-Plasticity Dilemma in Outdoor Class-Incremental 3D Object Detection — arXiv:2611.03229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc83f0e6b76f; sha256 5cd63251c54992911cadf55d21292c176f3e82b31026e4d99d361c15f93871d7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Class-incremental learning (CIL) for outdoor 3D object detection remains largely underexplored. Existing outdoor studies are limited to single-benchmark evaluations, with SDCoT++ considering KITTI and CL2OD considering nuScenes under different incremental settings. This makes it difficult to assess whether observed continual-learning behavior generalizes across autonomous-driving benchmarks. To the best of our knowledge, we provide the first unified cross-benchmark analysis of outdoor class-incremental 3D object detection across multiple autonomous-driving benchmarks, covering both two-task and multi-stage settings. We investigate: (1) how severely existing 3D detectors forget previously learned classes, (2) how incremental training exposes the stability-plasticity dilemma between knowledge retention and new-class acquisition, and (3) which forms of supervision are most effective for balancing these objectives. We introduce CL3DOD, a class-incremental 3D detection framework that restores missing supervision for previous classes using predictions from the previous-stage detector, preserves old-class responses through query-wise knowledge distillation, and employs EMA-based temporal consistency regularization. Experiments on KITTI and nuScenes reveal a consistent stability-plasticity dilemma across both benchmarks. CL3DOD generally achieves a more favorable stability-plasticity balance than controlled incremental baselines and improves upon published prior methods in the reported benchmark comparisons. This advantage persists across multiple incremental stages, demonstrating strong retention of previously learned knowledge while maintaining effective new-class acquisition. Our code, evaluation setup, and incremental task splits will be publicly released.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.03229 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:06:37.627Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).