AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation

arXiv:2404.05667v1 Announce Type: new
Abstract: A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accuracy of seen classes rather than unseen classes, while the latter is the true target to pursue. This issue becomes more significant in zero-shot image segmentation because the stronger (i.e., pixel-level) supervision brings a larger gap between seen and unseen classes. To mitigate it, we propose a novel architecture named AlignZeg, which …

abstract accuracy arxiv cs.cv improving issue performance recognition segmentation semantic true type visual zero-shot