Incremental Learning in Semantic Segmentation From Image Labels

Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 4371-4381

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 a localizer, 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 localizer. 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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cermelli_2022_CVPR, author = {Cermelli, Fabio and Fontanel, Dario and Tavera, Antonio and Ciccone, Marco and Caputo, Barbara}, title = {Incremental Learning in Semantic Segmentation From Image Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4371-4381} }