EUVIMEDEUVIMED entdecken
Crossref

Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection

Huajun Zhou, Peijia Chen, Lingxiao Yang, Xiaohua Xie, Jianhuang Lai

IEEE Transactions on Circuits and Systems for Video Technology · 2023-02 · 33 (2) · 743-755

DOI: 10.1109/tcsvt.2022.3203595 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-02. Verfasst von Huajun Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 97 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China, Project of Natural Resources Department of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper focuses on the Unsupervised Salient Object Detection (USOD) issue. We come up with a two-stage Activation-to-Saliency (A2S) framework that effectively excavates saliency cues to train a robust saliency detector. It is worth noting that our method does not require any manual annotation in the whole process. In the first stage, we transform an unsupervisedly pre-trained network to aggregate multi-level features into a single activation map, where an Adaptive Decision Boundary (ADB) is proposed to assist the training of the transformed network. Moreover, a new loss function is proposed to facilitate the generation of high-quality pseudo labels. In the second stage, a self-rectification learning strategy is developed to train a saliency detector and refine the pseudo labels online. In addition, we construct a lightweight saliency detector using two Residual Attention Modules (RAMs) to learn robust saliency information. Extensive experiments on several SOD benchmarks prove that our framework reports significant performance compared with existing USOD methods. Moreover, training our framework on 3,000 images consumes about 1 hour, which is over 10 times faster than previous state-of-the-art methods. Code has been published at https://github.com/moothes/A2S-USOD.

Förderung

  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China
  • Project of Natural Resources Department of Guangdong Province
  • Guangdong NSF Project

Zitieren

APA

Zhou, H., Chen, P., Yang, L., Xie, X., & Lai, J. (2023). Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 743-755. https://doi.org/10.1109/tcsvt.2022.3203595

Vancouver

Zhou H, Chen P, Yang L, Xie X, Lai J. Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(2):743-755. doi:10.1109/tcsvt.2022.3203595

BibTeX
@article{Zhou2023,
  author = {Zhou, Huajun and Chen, Peijia and Yang, Lingxiao and Xie, Xiaohua and Lai, Jianhuang},
  title = {Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {2},
  pages = {743--755},
  doi = {10.1109/tcsvt.2022.3203595}
}
Kostenlos starten →