GREx: 通用指称表达分割、理解和生成
GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation
AI总结：
GREx提出通用指称表达分割、理解和生成框架，扩展至多目标和无目标表达，引入gRefCOCO数据集和ReLA方法，提升复杂关系建模能力。
摘要：
指称表达分割（RES）和理解（REC）分别对表达所描述的对象进行分割和检测，而指称表达生成（REG）为所选对象生成表达。现有数据集和方法通常只支持单目标表达，即一个表达指代一个对象，不考虑多目标和无目标表达。这极大地限制了REx（RES/REC/REG）的实际应用。本文引入了三个新的基准，称为通用指称表达分割（GRES）、理解（GREC）和生成（GREG），统称为GREx，扩展了经典的REx，使表达能够识别任意数量的对象。我们构建了第一个大规模的GREx数据集gRefCOCO，其中包含多目标、无目标和单目标表达及其对应的图像，并有标记的目标。GREx和gRefCOCO被设计为与REx兼容，便于进行广泛的实验，以研究现有REx方法在GREx任务上的性能差距。GRES/GREC的一个挑战是复杂的关系建模，为此我们提出了一个基线ReLA，能够自适应地将图像划分为带有子实例线索的区域，并显式建模区域-区域和区域-语言依赖性。所提出的ReLA在GRES和GREC任务上均取得了最先进的结果。所提出的gRefCOCO数据集和方法可在https://henghuiding.github.io/GREx获取。
英文摘要：
Referring Expression Segmentation (RES) and Comprehension (REC) respectively segment and detect the object described by an expression, while Referring Expression Generation (REG) generates an expression for the selected object. Existing datasets and methods commonly support single-target expressions only, i.e., one expression refers to one object, not considering multi-target and no-target expressions. This greatly limits the real applications of REx (RES/REC/REG). This paper introduces three new benchmarks called Generalized Referring Expression Segmentation (GRES), Comprehension (GREC), and Generation (GREG), collectively denoted as GREx, which extend the classic REx to allow expressions to identify an arbitrary number of objects. We construct the first large-scale GREx dataset gRefCOCO that contains multi-target, no-target, and single-target expressions and their corresponding images with labeled targets. GREx and gRefCOCO are designed to be backward-compatible with REx, facilitating extensive experiments to study the performance gap of the existing REx methods on GREx tasks. One of the challenges of GRES/GREC is complex relationship modeling, for which we propose a baseline ReLA that adaptively divides the image into regions with sub-instance clues and explicitly models the region-region and region-language dependencies. The proposed ReLA achieves the state-of-the-art results on the both GRES and GREC tasks. The proposed gRefCOCO dataset and method are available at https://henghuiding.github.io/GREx.
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。
