EUVIMEDEUVIMED entdecken
Crossref

Non-exemplar Domain Incremental Object Detection via Learning Domain Bias

Xiang Song, Yuhang He, Songlin Dong, Yihong Gong

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (13) · 15056-15065

DOI: 10.1609/aaai.v38i13.29427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xiang Song und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Domain incremental object detection (DIOD) aims to gradually learn a unified object detection model from a dataset stream composed of different domains, achieving good performance in all encountered domains. The most critical obstacle to this goal is the catastrophic forgetting problem, where the performance of the model improves rapidly in new domains but deteriorates sharply in old ones after a few sessions. To address this problem, we propose a non-exemplar DIOD method named learning domain bias (LDB), which learns domain bias independently at each new session, avoiding saving examples from old domains. Concretely, a base model is first obtained through training during session 1. Then, LDB freezes the weights of the base model and trains individual domain bias for each new incoming domain, adapting the base model to the distribution of new domains. At test time, since the domain ID is unknown, we propose a domain selector based on nearest mean classifier (NMC), which selects the most appropriate domain bias for a test image. Extensive experimental evaluations on two series of datasets demonstrate the effectiveness of the proposed LDB method in achieving high accuracy on new and old domain datasets. The code is available at https://github.com/SONGX1997/LDB.

Zitieren

APA

Song, X., He, Y., Dong, S., & Gong, Y. (2024). Non-exemplar Domain Incremental Object Detection via Learning Domain Bias. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 15056-15065. https://doi.org/10.1609/aaai.v38i13.29427

Vancouver

Song X, He Y, Dong S, Gong Y. Non-exemplar Domain Incremental Object Detection via Learning Domain Bias. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(13):15056-15065. doi:10.1609/aaai.v38i13.29427

BibTeX
@article{Song2024,
  author = {Song, Xiang and He, Yuhang and Dong, Songlin and Gong, Yihong},
  title = {Non-exemplar Domain Incremental Object Detection via Learning Domain Bias},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {13},
  pages = {15056--15065},
  doi = {10.1609/aaai.v38i13.29427}
}
Kostenlos starten →