IFSENet : Harnessing Sparse Iterations for Interactive Few-shot Segmentation Excellence

arXiv:2403.15089v1 Announce Type: new
Abstract: Training a computer vision system to segment a novel class typically requires collecting and painstakingly annotating lots of images with objects from that class. Few-shot segmentation techniques reduce the required number of images to learn to segment a new class, but careful annotations of object boundaries are still required. On the other hand, interactive segmentation techniques only focus on incrementally improving the segmentation of one object at a time (typically, using clicks given by an …

abstract annotations arxiv class computer computer vision cs.cv few-shot images interactive learn novel object objects reduce segment segmentation training type vision