EUVIMEDEUVIMED entdecken
Crossref

Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation

Minhyun Lee, Seungho Lee, Jongwuk Lee, Hyunjung Shim

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-10 · 45 (10) · 12341-12357

DOI: 10.1109/tpami.2023.3273592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-10. Verfasst von Minhyun Lee und 3 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: Basic Science Research Program, NRF Korea, MSIP.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing studies on semantic segmentation using image-level weak supervision have several limitations, including sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, an improved version of Explicit Pseudo-pixel Supervision (EPS++), which learns from pixel-level feedback by combining two types of weak supervision. Specifically, the image-level label provides the object identity via the localization map, and the saliency map from an off-the-shelf saliency detection model offers rich object boundaries. We devise a joint training strategy to fully utilize the complementary relationship between disparate information. Notably, we suggest an Inconsistent Region Drop (IRD) strategy, which effectively handles errors in saliency maps using fewer hyper-parameters than EPS. Our method can obtain accurate object boundaries and discard co-occurring pixels, significantly improving the quality of pseudo-masks. Experimental results show that EPS++ effectively resolves the key challenges of semantic segmentation using weak supervision, resulting in new state-of-the-art performances on three benchmark datasets in a weakly supervised semantic segmentation setting. Furthermore, we show that the proposed method can be extended to solve the semi-supervised semantic segmentation problem using image-level weak supervision. Surprisingly, the proposed model also achieves new state-of-the-art performances on two popular benchmark datasets.

Förderung

  • Basic Science Research Program
  • NRF Korea
  • MSIP
  • MOE
  • IITP
  • Artificial Intelligence Graduate School Program

Zitieren

APA

Lee, M., Lee, S., Lee, J., & Shim, H. (2023). Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 12341-12357. https://doi.org/10.1109/tpami.2023.3273592

Vancouver

Lee M, Lee S, Lee J, Shim H. Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(10):12341-12357. doi:10.1109/tpami.2023.3273592

BibTeX
@article{Lee2023,
  author = {Lee, Minhyun and Lee, Seungho and Lee, Jongwuk and Shim, Hyunjung},
  title = {Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {10},
  pages = {12341--12357},
  doi = {10.1109/tpami.2023.3273592}
}
Kostenlos starten →