EUVIMEDEUVIMED entdecken
Crossref

Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation

Rongtao Xu, Changwei Wang, Jiaxi Sun, Shibiao Xu, Weiliang Meng, Xiaopeng Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3045-3053

DOI: 10.1609/aaai.v37i3.25408 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Rongtao Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 67-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high training efficiency. However, current methods suffer from insufficient extraction of comprehensive semantic information, resulting in low-quality pseudo-labels and sub-optimal solutions for end-to-end WSSS. To this end, we propose a simple and novel Self Correspondence Distillation (SCD) method to refine pseudo-labels without introducing external supervision. Our SCD enables the network to utilize feature correspondence derived from itself as a distillation target, which can enhance the network's feature learning process by complementing semantic information. In addition, to further improve the segmentation accuracy, we design a Variation-aware Refine Module to enhance the local consistency of pseudo-labels by computing pixel-level variation. Finally, we present an efficient end-to-end Transformer-based framework (TSCD) via SCD and Variation-aware Refine Module for the accurate WSSS task. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets demonstrate that our method significantly outperforms other state-of-the-art methods. Our code is available at https://github.com/Rongtao-Xu/RepresentationLearning/tree/main/SCD-AAAI2023.

Zitieren

APA

Xu, R., Wang, C., Sun, J., Xu, S., Meng, W., & Zhang, X. (2023). Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3045-3053. https://doi.org/10.1609/aaai.v37i3.25408

Vancouver

Xu R, Wang C, Sun J, Xu S, Meng W, Zhang X. Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3045-3053. doi:10.1609/aaai.v37i3.25408

BibTeX
@article{Xu2023,
  author = {Xu, Rongtao and Wang, Changwei and Sun, Jiaxi and Xu, Shibiao and Meng, Weiliang and Zhang, Xiaopeng},
  title = {Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {3},
  pages = {3045--3053},
  doi = {10.1609/aaai.v37i3.25408}
}
Kostenlos starten →