EUVIMEDEUVIMED entdecken
Crossref

Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels

Yikai Wang, Yanwei Fu, Xinwei Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3242-3256

DOI: 10.1109/tpami.2023.3338268 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Yikai Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A noisy training set usually leads to the degradation of the generalization and robustness of neural networks. In this article, we propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels. Specifically, we first present a Scalable Penalized Regression (SPR) method, to model the linear relation between network features and one-hot labels. In SPR, the clean data are identified by the zero mean-shift parameters solved in the regression model. We theoretically show that SPR can recover clean data under some conditions. Under general scenarios, the conditions may be no longer satisfied; and some noisy data are falsely selected as clean data. To solve this problem, we propose a data-adaptive method for Scalable Penalized Regression with Knockoff filters (Knockoffs-SPR), which is provable to control the False-Selection-Rate (FSR) in the selected clean data. To improve the efficiency, we further present a split algorithm that divides the whole training set into small pieces that can be solved in parallel to make the framework scalable to large datasets. While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data. Experimental results on several benchmark datasets and real-world noisy datasets show the effectiveness of our framework and validate the theoretical results of Knockoffs-SPR.

Förderung

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

Zitieren

APA

Wang, Y., Fu, Y., & Sun, X. (2024). Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3242-3256. https://doi.org/10.1109/tpami.2023.3338268

Vancouver

Wang Y, Fu Y, Sun X. Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3242-3256. doi:10.1109/tpami.2023.3338268

BibTeX
@article{Wang2024,
  author = {Wang, Yikai and Fu, Yanwei and Sun, Xinwei},
  title = {Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {5},
  pages = {3242--3256},
  doi = {10.1109/tpami.2023.3338268}
}
Kostenlos starten →