EUVIMEDEUVIMED entdecken
Crossref

Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling

Beichen Zhang, Liang Li, Shuhui Wang, Shaofei Cai, Zheng-Jun Zha, Qi Tian, Qingming Huang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9780-9796

DOI: 10.1109/tpami.2024.3432099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Beichen Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Active learning (AL) is to design label-efficient algorithms by labeling the most representative samples. It reduces annotation cost and attracts increasing attention from the community. However, previous AL methods suffer from the inadequacy of annotations and unreliable uncertainty estimation. Moreover, we find that they ignore the intra-diversity of selected samples, which leads to sampling redundancy. In view of these challenges, we propose an inductive state-relabeling adversarial AL model (ISRA) that consists of a unified representation generator, an inductive state-relabeling discriminator, and a heuristic clique rescaling module. The generator introduces contrastive learning to leverage unlabeled samples for self-supervised training, where the mutual information is utilized to improve the representation quality for AL selection. Then, we design an inductive uncertainty indicator to learn the state score from labeled data and relabel unlabeled data with different importance for better discrimination of instructive samples. To solve the problem of sampling redundancy, the heuristic clique rescaling module measures the intra-diversity of candidate samples and recurrently rescales them to select the most informative samples. The experiments conducted on eight datasets and two imbalanced scenarios show that our model outperforms the previous state-of-the-art AL methods. As an extension on the cross-modal AL task, we apply ISRA to the image captioning and it also achieves superior performance.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Zhang, B., Li, L., Wang, S., Cai, S., Zha, Z. J., Tian, Q., & Huang, Q. (2024). Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9780-9796. https://doi.org/10.1109/tpami.2024.3432099

Vancouver

Zhang B, Li L, Wang S, Cai S, Zha ZJ, Tian Q, et al. Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9780-9796. doi:10.1109/tpami.2024.3432099

BibTeX
@article{Zhang2024,
  author = {Zhang, Beichen and Li, Liang and Wang, Shuhui and Cai, Shaofei and Zha, Zheng-Jun and Tian, Qi and Huang, Qingming},
  title = {Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {9780--9796},
  doi = {10.1109/tpami.2024.3432099}
}
Kostenlos starten →