EUVIMEDEUVIMED entdecken
Crossref

Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy

Li Ding, Xiang Song, Yuhang He, Changxin Wang, Songlin Dong, Xing Wei, Yihong Gong

IEEE Transactions on Circuits and Systems for Video Technology · 2024-01 · 34 (1) · 424-437

DOI: 10.1109/tcsvt.2023.3285263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-01. Verfasst von Li Ding und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Key Research and Development Project of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection with the capacity to incrementally adapt to new domains is a crucial yet relatively under-explored research topic. The catastrophic forgetting problem presents a significant challenge to achieve this goal, where the model’s performance improves quickly in new conditions but deteriorates sharply in old ones after several incremental learning sessions. Drawing on recent discoveries in visual memories of the human brain, we introduce the Topology-Preserving Domain Incremental Object Detection (TP-DIOD) approach, which aims to address the catastrophic forgetting problem by extracting the topological structure of the feature space learned by the Convolutional Neural Network (CNN) model and preserving this topology during the subsequent incremental learning sessions. Specifically, we model the feature space topology using the self-organizing map (SOM) and construct an anchor image set based on the centroid vectors of the SOM nodes to memorize the feature space topology. We then develop the anchor loss function to penalize the topological changes of the feature space during the subsequent incremental learning sessions. Experimental evaluations on two sets of datasets demonstrate the effectiveness of the proposed TP-DIOD method in mitigating the catastrophic forgetting problem and achieving high accuracy on both old and new domain datasets.

Förderung

  • National Key Research and Development Project of China
  • National Natural Science Foundation of China

Zitieren

APA

Ding, L., Song, X., He, Y., Wang, C., Dong, S., Wei, X., & Gong, Y. (2024). Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy. IEEE Transactions on Circuits and Systems for Video Technology, 34(1), 424-437. https://doi.org/10.1109/tcsvt.2023.3285263

Vancouver

Ding L, Song X, He Y, Wang C, Dong S, Wei X, et al. Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(1):424-437. doi:10.1109/tcsvt.2023.3285263

BibTeX
@article{Ding2024,
  author = {Ding, Li and Song, Xiang and He, Yuhang and Wang, Changxin and Dong, Songlin and Wei, Xing and Gong, Yihong},
  title = {Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {1},
  pages = {424--437},
  doi = {10.1109/tcsvt.2023.3285263}
}
Kostenlos starten →