Group-On：利用支持性查询增强单样本分割
Group-On: Boosting One-Shot Segmentation with Supportive Query
AI总结：
针对单样本语义分割中的类内变化问题，本文提出 Group-On，通过批量查询互为伪支持并结合 MoME 路由专家机制，显著提升性能。
摘要：
单样本语义分割旨在仅给定同一类别的一张带标注支持图像的情况下，对查询图像进行分割。这项任务具有挑战性，因为支持图像和查询图像中的目标物体在外观和姿态上可能存在很大差异（即类内变化）。以往工作表明，在少样本设置中加入更多带标注支持图像可以提升性能，但由于需要额外的人工标注，也会增加成本。本文提出了一种新颖且有效的单样本语义分割方法，称为 Group-On，它将多张查询图像成批打包，以便在同一类别内实现相互的知识支持。具体而言，在预测出该批查询的粗分割掩码后，查询-掩码对充当伪支持数据，以相互增强掩码预测。为有效引导这一过程，我们构建了创新的 MoME 模块，其中数量灵活的掩码专家由场景驱动的路由器引导，并协同作出全面决策，充分促进查询之间的互利。在三个标准基准上的综合实验表明，在单样本设置下，Group-On 以相当大的幅度显著优于以往工作。仅使用一张带标注支持图像，Group-On 甚至能够与使用 5 张带标注图像的同类方法相竞争。
英文摘要：
One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class. This task is challenging because target objects in the support and query images can be largely different in appearance and pose (i.e., intra-class variation). Prior works suggested that incorporating more annotated support images in few-shot settings boosts performances but increases costs due to additional manual labeling. In this paper, we propose a novel and effective approach for ONE-shot semantic segmentation, called Group-On, which packs multiple query images in batches for the benefit of mutual knowledge support within the same category. Specifically, after coarse segmentation masks of the batch of queries are predicted, query-mask pairs act as pseudo support data to enhance mask predictions mutually. To effectively steer such process, we construct an innovative MoME module, where a flexible number of mask experts are guided by a scene-driven router and work together to make comprehensive decisions, fully promoting mutual benefits of queries. Comprehensive experiments on three standard benchmarks show that, in the ONE-shot setting, Group-On significantly outperforms previous works by considerable margins. With only one annotated support image, Group-On can be even competitive with the counterparts using 5 annotated images.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
