EUVIMEDEUVIMED entdecken
Crossref

YOLO-IOD: Towards Real Time Incremental Object Detection

Shizhou Zhang, Xueqiang Lv, Yinghui Xing, Qirui Wu, Di Xu, Chen Zhao, Yanning Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12744-12752

DOI: 10.1609/aaai.v40i15.38271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shizhou Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current methodologies for incremental object detection (IOD) primarily rely on Faster R-CNN or DETR series detectors; however, these approaches do not accommodate the real-time YOLO detection frameworks. In this paper, we first identify three primary types of knowledge conflicts that contribute to catastrophic forgetting in YOLO-based incremental detectors: foreground-background confusion, parameter interference, and misaligned knowledge distillation. Subsequently, we introduce YOLO-IOD, a real-time Incremental Object Detection (IOD) framework that is constructed upon the pretrained YOLO-World model, facilitating incremental learning via a stage-wise parameter-efficient finetuning process. Specifically, YOLO-IOD encompasses three principal components: 1) Conflict-Aware Pseudo-Label Refinement (CPR), which mitigates the foreground-background confusion by leveraging the confidence levels of pseudo labels and identifying potential objects relevant to future tasks. 2) Importance-based Kernel Selection (IKS), which identifies and updates the pivotal convolution kernels pertinent to the current task during the current learning stage. 3)Cross-Stage Asymmetric Knowledge Distillation (CAKD), which addresses the misaligned knowledge distillation conflict by transmitting the features of the student target detector through the detection heads of both the previous and current teacher detectors, thereby facilitating asymmetric distillation between existing and newly introduced categories. We further introduce LoCo COCO, a more realistic benchmark that eliminates data leakage across stages. Experiments on both conventional and LoCo COCO benchmarks show that YOLO-IOD achieves superior performance with minimal forgetting.

Zitieren

APA

Zhang, S., Lv, X., Xing, Y., Wu, Q., Xu, D., Zhao, C., & Zhang, Y. (2026). YOLO-IOD: Towards Real Time Incremental Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12744-12752. https://doi.org/10.1609/aaai.v40i15.38271

Vancouver

Zhang S, Lv X, Xing Y, Wu Q, Xu D, Zhao C, et al. YOLO-IOD: Towards Real Time Incremental Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12744-12752. doi:10.1609/aaai.v40i15.38271

BibTeX
@article{Zhang2026,
  author = {Zhang, Shizhou and Lv, Xueqiang and Xing, Yinghui and Wu, Qirui and Xu, Di and Zhao, Chen and Zhang, Yanning},
  title = {YOLO-IOD: Towards Real Time Incremental Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {15},
  pages = {12744--12752},
  doi = {10.1609/aaai.v40i15.38271}
}
Kostenlos starten →