使用连接组约束的果蝇模型进行建筑图纸中一次性影线识别的主动视觉采样
What Survives on Real Drawings: Active Sampling, Connectome Wiring, and Matched Baselines in Architectural Document Vision
- Independent Researcher（独立研究者）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究测试受连接组约束的果蝇视觉网络能否作为建筑图纸填充图案的一次性匹配描述符，结果支持迁移与主动采样，但生物布线优势不显著。
AI中文摘要：
建筑图纸通过重复的填充图案编码材料类别。我们测试了一个受连接组约束的果蝇视觉网络，该网络预训练用于运动，是否可以在不进行任务特定权重更新的情况下，被重新用作一次性填充匹配的描述符。每个64×64的补丁沿八条扫描轨迹平移，并在57种细胞类型中汇总；查询描述符随后与每个类别的一个图例条带进行匹配。在基于CubiCasa5K几何构建的合成基准的400张开发图纸上，冻结的果蝇流程达到0.857的面积加权准确率，使用扩展图例时达到0.910。在等亮度方向条件下，其达到0.840，而十一种像素统计量仅为0.299，Gabor滤波器组达到0.900。将漂移替换为重复的静止帧会使组合等条件得分降低0.089 [0.066, 0.112]。然而，仅受体描述符达到0.891，任务训练的5,888参数CNN平均达到0.959，因此当前证据支持迁移和主动采样的有用性，但不支持生物布线的优势。我们将项目记录的结果与重新计算的检查分开，并报告了一次小型真实图纸审计。因此，所支持的论断是狭窄的：面向运动的生物视觉可以被重新用作建筑填充匹配的有用纹理表示，而拓扑贡献和端到端BIM实用性仍是开放问题。
英文摘要：
A connectome-constrained model of the fly visual system, optimized for motion and then frozen, can be driven over architectural drawings by prescribed motion and used as a texture representation. We compare it with information-matched baselines that see the same 721 photoreceptor samples. On clean synthetic data the frozen model transfers but loses to task training: 0.857 area-weighted accuracy in one-shot hatch matching versus 0.959 for a 5,888-parameter CNN, and 0.619 IoU in wall segmentation versus 0.905 for a matched network. Under scan noise and thickened strokes, the trained networks lose up to 0.188 accuracy while the frozen pipeline loses 0.030. On fourteen production sheets, opened once, a 1,876-parameter fly model reaches 0.505 average precision versus 0.415 for a network two hundred times larger. A preregistered held-out split confirms the clean-data ordering: 0.835 for the circuit, 0.894 for receptors only, and 0.971-0.980 for trained CNNs. Rewiring the connectome while preserving degrees or type pairs and transmitter signs costs 0.271-0.356 accuracy across three seeds, so the exact wiring is load-bearing. Yet the intact circuit does not beat its moving retina, and T4/T5 silencing leaves both tasks intact. Longer observations reverse the circuit-receptor ordering once the stimulus spans a period, but not through T4/T5. Thus active sampling and exact structure matter, while clean-data practical performance remains dominated by task-trained networks and the useful transfer margin is largely retinal.
