Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation

arXiv:2404.11981v1 Announce Type: new
Abstract: Weakly Incremental Learning for Semantic Segmentation (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. However, a scenario usually arises where a pixel is concurrently predicted as an old class by the pre-trained segmentation model and a new class by the seed areas. Such …

abstract arxiv class cost cs.cv form image incremental labels pixel seed segment segmentation semantic solve supervision type