EUVIMEDEUVIMED entdecken
Crossref

De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection

Kuo Wang, Jingyu Zhuang, Guanbin Li, Chaowei Fang, Lechao Cheng, Liang Lin, Fan Zhou

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 2573-2580

DOI: 10.1609/aaai.v37i2.25355 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Kuo Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most of the recent research in semi-supervised object detection follows the pseudo-labeling paradigm evolved from the semi-supervised image classification task. However, the training paradigm of the two-stage object detector inevitably makes the pseudo-label learning process for unlabeled images full of bias. Specifically, the IoU matching scheme used for selecting and labeling candidate boxes is based on the assumption that the matching source~(ground truth) is accurate enough in terms of the number of objects, object position and object category. Obviously, pseudo-labels generated for unlabeled images cannot satisfy such a strong assumption, which makes the produced training proposals extremely unreliable and thus severely spoil the follow-up training. To de-bias the training proposals generated by the pseudo-label-based IoU matching, we propose a general framework -- De-biased Teacher, which abandons both the IoU matching and pseudo labeling processes by directly generating favorable training proposals for consistency regularization between the weak/strong augmented image pairs. Moreover, a distribution-based refinement scheme is designed to eliminate the scattered class predictions of significantly low values for higher efficiency. Extensive experiments demonstrate that the proposed De-biased Teacher consistently outperforms other state-of-the-art methods on the MS-COCO and PASCAL VOC benchmarks. Source codes are available at https://github.com/wkfdb/De-biased-Teracher.

Zitieren

APA

Wang, K., Zhuang, J., Li, G., Fang, C., Cheng, L., Lin, L., & Zhou, F. (2023). De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 2573-2580. https://doi.org/10.1609/aaai.v37i2.25355

Vancouver

Wang K, Zhuang J, Li G, Fang C, Cheng L, Lin L, et al. De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):2573-2580. doi:10.1609/aaai.v37i2.25355

BibTeX
@article{Wang2023,
  author = {Wang, Kuo and Zhuang, Jingyu and Li, Guanbin and Fang, Chaowei and Cheng, Lechao and Lin, Liang and Zhou, Fan},
  title = {De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {2},
  pages = {2573--2580},
  doi = {10.1609/aaai.v37i2.25355}
}
Kostenlos starten →