基于视觉语言真伪验证的零样本指代表达理解
Zero-Shot Referring Expression Comprehension via Vison-Language True/False Verification
AI总结：
本研究针对零样本指代表达理解任务，提出将任务重构为逐框视觉语言真伪验证的无微调工作流，在多个基准上性能优于相关基线，证明工作流设计比任务预训练更关键。
摘要：
指代表达理解（REC）通常采用经任务训练的定位模型解决。本研究表明，无需任何REC专项训练的零样本工作流即可取得有竞争力甚至更优的性能。我们的方法将REC重构为逐框视觉语言验证任务：给定COCO-clean通用检测器YOLO-World生成的候选框，通用视觉语言模型（VLM）独立对每个区域回答真伪查询。该简单流程可减少跨框干扰，支持弃权（不执行）与多匹配，且无需微调。在RefCOCO、RefCOCO+和RefCOCOg数据集上，我们的方法不仅优于零样本GroundingDINO基线，还超过了经REC训练的GroundingDINO及GroundingDINO+CRG的已报道结果。采用相同候选框的对照实验证实，验证范式显著优于基于选择的提示方法，且该结果在开源VLM上同样成立。总体而言，我们证明工作流设计而非任务特定预训练，是实现优异零样本REC性能的核心驱动因素。
英文摘要：
Referring Expression Comprehension (REC) is usually addressed with task-trained grounding models. We show that a zero-shot workflow, without any REC-specific training, can achieve competitive or superior performance. Our approach reformulates REC as box-wise visual-language verification: given proposals from a COCO-clean generic detector (YOLO-World), a general-purpose VLM independently answers True/False queries for each region. This simple procedure reduces cross-box interference, supports abstention and multiple matches, and requires no fine-tuning. On RefCOCO, RefCOCO+, and RefCOCOg, our method not only surpasses a zero-shot GroundingDINO baseline but also exceeds reported results for GroundingDINO trained on REC and GroundingDINO+CRG. Controlled studies with identical proposals confirm that verification significantly outperforms selection-based prompting, and results hold with open VLMs. Overall, we show that workflow design, rather than task-specific pretraining, drives strong zero-shot REC performance.
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。
