EUVIMEDEUVIMED entdecken
Crossref

Spatial Structure Constraints for Weakly Supervised Semantic Segmentation

Tao Chen, Yazhou Yao, Xingguo Huang, Zechao Li, Liqiang Nie, Jinhui Tang

IEEE Transactions on Image Processing · 2024 · 33 · 1136-1148

DOI: 10.1109/tip.2024.3359041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Tao Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 97 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based techniques have been widely adopted to provide object location clues. Considering class activation maps (CAMs) can only locate the most discriminative part of objects, recent approaches usually adopt an expansion strategy to enlarge the activation area for more integral object localization. However, without proper constraints, the expanded activation will easily intrude into the background region. In this paper, we propose spatial structure constraints (SSC) for weakly supervised semantic segmentation to alleviate the unwanted object over-activation of attention expansion. Specifically, we propose a CAM-driven reconstruction module to directly reconstruct the input image from deep CAM features, which constrains the diffusion of last-layer object attention by preserving the coarse spatial structure of the image content. Moreover, we propose an activation self-modulation module to refine CAMs with finer spatial structure details by enhancing regional consistency. Without external saliency models to provide background clues, our approach achieves 72.7% and 47.0% mIoU on the PASCAL VOC 2012 and COCO datasets, respectively, demonstrating the superiority of our proposed approach. The source codes and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/SSC.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • China Postdoctoral Science Foundation
  • Jiangsu Funding Program for Excellent Postdoctoral Talent
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Chen, T., Yao, Y., Huang, X., Li, Z., Nie, L., & Tang, J. (2024). Spatial Structure Constraints for Weakly Supervised Semantic Segmentation. IEEE Transactions on Image Processing, 33, 1136-1148. https://doi.org/10.1109/tip.2024.3359041

Vancouver

Chen T, Yao Y, Huang X, Li Z, Nie L, Tang J. Spatial Structure Constraints for Weakly Supervised Semantic Segmentation. IEEE Transactions on Image Processing. 2024;33:1136-1148. doi:10.1109/tip.2024.3359041

BibTeX
@article{Chen2024,
  author = {Chen, Tao and Yao, Yazhou and Huang, Xingguo and Li, Zechao and Nie, Liqiang and Tang, Jinhui},
  title = {Spatial Structure Constraints for Weakly Supervised Semantic Segmentation},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {1136--1148},
  doi = {10.1109/tip.2024.3359041}
}
Kostenlos starten →