English

Incremental Learning in Semantic Segmentation from Image Labels

Computer Vision and Pattern Recognition 2022-04-04 v3

Abstract

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the auxiliary classifier. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision. Code can be found at https://github.com/fcdl94/WILSON.

Keywords

Cite

@article{arxiv.2112.01882,
  title  = {Incremental Learning in Semantic Segmentation from Image Labels},
  author = {Fabio Cermelli and Dario Fontanel and Antonio Tavera and Marco Ciccone and Barbara Caputo},
  journal= {arXiv preprint arXiv:2112.01882},
  year   = {2022}
}

Comments

To appear in CVPR 22

R2 v1 2026-06-24T08:03:05.513Z