EUVIMEDEUVIMED entdecken
Crossref

Salvage of Supervision in Weakly Supervised Object Detection and Segmentation

Lin Sui, Chen-Lin Zhang, Jianxin Wu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-08 · 45 (8) · 10394-10408

DOI: 10.1109/tpami.2023.3243054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-08. Verfasst von Lin Sui und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Algorithms, Benchmarking. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised vision tasks, including detection and segmentation, have attracted much attention in the vision community recently. However, the lack of detailed and precise annotations in the weakly supervised case leads to a large accuracy gap between weakly- and fully-supervised methods. In this article, we propose a new framework, Salvage of Supervision (SoS), with the key idea being to effectively harness every potentially useful supervisory signal in weakly supervised vision tasks. Starting with weakly supervised object detection (WSOD), we propose SoS-WSOD to shrink the technology gap between WSOD and FSOD, which utilizes the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection for WSOD. Moreover, SoS-WSOD removes restrictions in traditional WSOD methods, including the reliance on ImageNet pretraining and inability to use modern backbones. The SoS framework also extends to weakly supervised semantic segmentation and instance segmentation. On several weakly supervised vision benchmarks, SoS achieves significant performance boost and generalization ability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsBenchmarkingSemanticsSupervised Machine Learning

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Sui, L., Zhang, C. L., & Wu, J. (2023). Salvage of Supervision in Weakly Supervised Object Detection and Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 10394-10408. https://doi.org/10.1109/tpami.2023.3243054

Vancouver

Sui L, Zhang CL, Wu J. Salvage of Supervision in Weakly Supervised Object Detection and Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(8):10394-10408. doi:10.1109/tpami.2023.3243054

BibTeX
@article{Sui2023,
  author = {Sui, Lin and Zhang, Chen-Lin and Wu, Jianxin},
  title = {Salvage of Supervision in Weakly Supervised Object Detection and Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {8},
  pages = {10394--10408},
  doi = {10.1109/tpami.2023.3243054}
}
Kostenlos starten →