Topo-R1: 通过视觉-语言模型检测拓扑异常
Topo-R1: Detecting Topological Anomalies via Vision-Language Models
AI总结：
本文通过构建拓扑感知基准Topo-R1，评估视觉-语言模型在检测管状网络拓扑异常中的能力，发现现有模型缺乏拓扑感知，提出基于拓扑感知奖励的联合评分方法，显著提升模型在ID和OOD测试中的性能。
摘要：
拓扑学在血 vessels、神经纤维和道路网络等管状结构中至关重要，其中连通性和环状结构决定了下游功能分析。视觉-语言模型（VLMs）因其推理和 grounding 能力被认为是理解此类结构的有力候选者。为了探索其拓扑感知能力，我们系统评估了领先的闭源和开源VLMs，在管状网络分割掩码中定位和分类四种经典拓扑异常（断裂/虚假连接、缺失/额外分支）。它们的性能接近随机，表明当前通用VLMs缺乏拓扑感知。由于没有现有资源将分割掩码与局部异常注解放在一起，我们构建了一个自动化、多领域数据整理流水线，合成多样化的拓扑扰动，并在不同难度级别上生成可验证的Betti数注释，从而产生第一个系统化的基准，包含大规模训练集和保留的in-distribution（ID）和out-of-distribution（OOD）测试套件。基于此基准，我们引入了Topo-R1，其核心是一个拓扑感知的复合奖励，联合评分定位、分类和骨架级结构保真度。监督微调启动了符合模式的输出，然后Group Relative Policy Optimization（GRPO）则基于此奖励优化策略，使预测朝着拓扑有意义的结构而非表面像素重叠方向发展。大量实验表明，Topo-R1在ID和OOD测试以及真实分割输出协议中显著优于通用VLMs，并在匹配或超过监督基线方面表现优异，为基于VLM的结构视觉数据拓扑理解奠定了坚实基础。
英文摘要：
Topology is critical in tubular structures such as blood vessels, nerve fibers, and road networks, where connectivity and loop structure govern downstream functional analysis. Vision-Language Models (VLMs) are promising candidates for understanding such structures, given their reasoning and grounding capabilities. To probe their topological perception, we systematically evaluate leading closed- and open-source VLMs on localizing and classifying four canonical topological anomalies (broken/spurious connections, missing/extra branches) in tubular-network segmentation masks. They perform nearly at random, indicating that topology-aware perception is largely absent from current general-purpose VLMs. As no existing resource pairs segmentation masks with localized anomaly annotations, we build an automated, multi-domain data-curation pipeline that synthesizes diverse topological perturbations with verifiable Betti-number annotations across graduated difficulty levels, yielding the first systematic benchmark with a large-scale training set and held-out in-distribution (ID) and out-of-distribution (OOD) test suites. Building on this benchmark, we introduce Topo-R1, centered on a topology-aware composite reward that jointly scores localization, classification, and skeleton-level structural fidelity. Supervised fine-tuning cold-starts schema-compliant outputs, and Group Relative Policy Optimization (GRPO) then optimizes the policy against this reward, steering predictions toward topologically meaningful structure rather than superficial pixel overlap. Extensive experiments show that Topo-R1 substantially outperforms general-purpose VLMs and matches or exceeds supervised baselines across ID, OOD, and real-segmentation-output protocols, establishing a strong foundation for VLM-based topological understanding of structured visual data.
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。
