GRES：广义指代表达分割
GRES: Generalized Referring Expression Segmentation
AI总结：
针对经典RES仅支持单目标指代的局限，本文提出GRES基准与gRefCOCO数据集，并设计基于区域关系建模的ReLA基线，在广义和经典RES任务上均达到最先进性能。
摘要：
指代表达分割（Referring Expression Segmentation，RES）旨在为给定语言表达所描述的对象生成分割掩码。现有经典RES数据集和方法通常仅支持单目标表达，即一个表达指代一个目标对象，而未考虑多目标和无目标表达，这限制了RES在实际中的应用。本文提出一个名为广义指代表达分割（Generalized Referring Expression Segmentation，GRES）的新基准，将经典RES扩展为允许表达指代任意数量的目标对象。为此，我们构建了首个大规模GRES数据集gRefCOCO，其中包含多目标、无目标和单目标表达。GRES和gRefCOCO被设计为与RES具有良好兼容性，从而有助于开展大量实验，研究现有RES方法在GRES任务上的性能差距。在实验研究中，我们发现GRES的重大挑战之一是复杂关系建模。基于此，我们提出一种基于区域的GRES基线ReLA，它自适应地将图像划分为具有子实例线索的区域，并显式建模区域—区域以及区域—语言依赖关系。所提出的ReLA方法在新提出的GRES任务和经典RES任务上均取得了新的最先进性能。所提出的gRefCOCO数据集和方法可在https://henghuiding.github.io/GRES获取。
英文摘要：
Referring Expression Segmentation (RES) aims to generate a segmentation mask for the object described by a given language expression. Existing classic RES datasets and methods commonly support single-target expressions only, i.e., one expression refers to one target object. Multi-target and no-target expressions are not considered. This limits the usage of RES in practice. In this paper, we introduce a new benchmark called Generalized Referring Expression Segmentation (GRES), which extends the classic RES to allow expressions to refer to an arbitrary number of target objects. Towards this, we construct the first large-scale GRES dataset called gRefCOCO that contains multi-target, no-target, and single-target expressions. GRES and gRefCOCO are designed to be well-compatible with RES, facilitating extensive experiments to study the performance gap of the existing RES methods on the GRES task. In the experimental study, we find that one of the big challenges of GRES is complex relationship modeling. Based on this, we propose a region-based GRES 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 approach ReLA achieves new state-of-the-art performance on the both newly proposed GRES and classic RES tasks. The proposed gRefCOCO dataset and method are available at https://henghuiding.github.io/GRES.
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。
