Incremental Learning in Semantic Segmentation from Image Labels
This addresses the challenge of expensive pixel-level annotations for semantic segmentation, enabling more efficient model updates for applications like autonomous driving or medical imaging, though it is incremental as it builds on existing weakly-supervised and incremental learning approaches.
The paper tackles the problem of updating semantic segmentation models incrementally with new categories using only image-level labels, which are cheaper than pixel-level annotations, and achieves results comparable to fully supervised incremental learning methods on Pascal VOC and COCO datasets.
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.