VIRO：用于指代表达理解的鲁棒且高效的神经符号推理与验证
VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
AI总结：
VIRO通过在推理步骤中嵌入轻量级操作符验证器，提升指代表达理解的鲁棒性和效率，达到61.1%的平衡准确率。
摘要：
指代表达理解（REC）旨在定位与自然语言查询对应的图像区域。最近的神经符号 REC 方法利用大语言模型（LLMs）和视觉-语言模型（VLMs）进行组合推理，将查询分解为结构化程序并逐步执行。尽管这些方法实现了可解释的推理和强大的零样本泛化能力，但它们假设中间推理步骤是准确的。然而，这种假设会导致级联错误：假阳性检测和无效关系通过推理链传播，即使图像中没有目标，也会产生高置信度的假阳性。为了解决这一限制，我们引入了验证集成推理运算符（VIRO），一种神经符号框架，它在推理步骤中嵌入轻量级操作符级验证器。每个操作符执行并验证其输出，例如对象存在或空间关系，使系统能够通过验证感知的回避处理无目标情况。我们的框架实现了最先进的性能，在目标存在和无目标设置中达到61.1%的平衡准确率，并展示了对真实世界眼动数据的泛化能力。VIRO还表现出高可靠性，程序故障率最高为0.3%，具有高效的每查询运行时间，并通过解耦的程序生成和执行实现可扩展性。
英文摘要：
Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models (VLMs) to perform compositional reasoning, decomposing queries into structured programs and executing them step-by-step. While such approaches achieve interpretable reasoning and strong zero-shot generalization, they assume that intermediate reasoning steps are accurate. However, this assumption causes cascading errors: false detections and invalid relations propagate through the reasoning chain, yielding high-confidence false positives even when no target is present in the image. To address this limitation, we introduce Verification-Integrated Reasoning Operators (VIRO), a neuro-symbolic framework that embeds lightweight operator-level verifiers within reasoning steps. Each operator executes and validates its output, such as object existence or spatial relationships, allowing the system to robustly handle no-target cases through verification-aware abstention. Our framework achieves state-of-the-art performance, reaching 61.1% balanced accuracy across target-present and no-target settings, and demonstrates generalization to real-world egocentric data. VIRO also shows high reliability with a program failure rate of at most 0.3%, efficient per-query runtime, and scalability through decoupled program generation and execution.
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。
