Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation

Guiyang Chan, Pengcheng Zhang, Hai Dong, Shunhui Ji, Bainian Chen
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6155-6169, 2024.

Abstract

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://github.com/TranquilChan/PFA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-chan24b, title = {Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation}, author = {Chan, Guiyang and Zhang, Pengcheng and Dong, Hai and Ji, Shunhui and Chen, Bainian}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {6155--6169}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/chan24b/chan24b.pdf}, url = {https://proceedings.mlr.press/v235/chan24b.html}, abstract = {Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://github.com/TranquilChan/PFA.} }
Endnote
%0 Conference Paper %T Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation %A Guiyang Chan %A Pengcheng Zhang %A Hai Dong %A Shunhui Ji %A Bainian Chen %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-chan24b %I PMLR %P 6155--6169 %U https://proceedings.mlr.press/v235/chan24b.html %V 235 %X Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://github.com/TranquilChan/PFA.
APA
Chan, G., Zhang, P., Dong, H., Ji, S. & Chen, B.. (2024). Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:6155-6169 Available from https://proceedings.mlr.press/v235/chan24b.html.

Related Material