EUVIMEDEUVIMED entdecken
Crossref

Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation

Jingxuan He, Lechao Cheng, Chaowei Fang, Zunlei Feng, Tingting Mu, Mingli Song

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (3) · 2085-2093

DOI: 10.1609/aaai.v38i3.27980 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jingxuan He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compared to conventional semantic segmentation with pixel-level supervision, weakly supervised semantic segmentation (WSSS) with image-level labels poses the challenge that it commonly focuses on the most discriminative regions, resulting in a disparity between weakly and fully supervision scenarios. A typical manifestation is the diminished precision on object boundaries, leading to deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into certain regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we propose an adaptive masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that confident regions should be robust enough to preserve the global semantics, and introduce a complementary self-distillation method that constrains semantic consistency between confident regions and an augmented view with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art counterparts but also surpasses multi-stage methods that trade complexity for accuracy.

Zitieren

APA

He, J., Cheng, L., Fang, C., Feng, Z., Mu, T., & Song, M. (2024). Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2085-2093. https://doi.org/10.1609/aaai.v38i3.27980

Vancouver

He J, Cheng L, Fang C, Feng Z, Mu T, Song M. Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2085-2093. doi:10.1609/aaai.v38i3.27980

BibTeX
@article{He2024,
  author = {He, Jingxuan and Cheng, Lechao and Fang, Chaowei and Feng, Zunlei and Mu, Tingting and Song, Mingli},
  title = {Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {3},
  pages = {2085--2093},
  doi = {10.1609/aaai.v38i3.27980}
}
Kostenlos starten →