重新思考针对专业设计数据的预训练：来自JONES-19文化设计数据集的证据
Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
浏览论文内容
中文总结 AI 辅助
该研究以JONES-19文化设计数据集为对象，对比两种CNN训练策略，发现小型高质量设计数据集结合多裁剪采样，可替代大规模通用预训练，为专业设计领域的ML研究提供新思路。
中文摘要 AI 辅助
设计与建筑档案以图形形式编码了人类专家知识，为设计启发式机器学习（ML）挑战提供了关键测试平台，这类挑战是典型计算机视觉基准所不具备的。基于《装饰语法》（伦敦，1857）构建的小型图像数据集JONES-19，我们评估了卷积神经网络（CNNs）在两种模型训练策略中的判别性能：（a）针对通用领域“视觉常识”的ImageNet预训练；（b）在JONES-19的设计数据上从头开始学习。我们发现，尽管通用领域先验能提升判别性能，但通过重复局部采样（多裁剪）增强的从头学习可有效恢复这些增益。对于高度结构化的设计数据，由设计驱动的局部表示为学习提供了充足基础，挑战了对大规模通用预训练的依赖。这些发现表明，在专业设计领域，精心策划的、能捕捉经验与形式设计原则的小型高质量数据集，相比优先收集大规模数据，可能在揭示特定设计领域的本质方面更有效、更具信息性。
英文摘要
Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer vision benchmarks. Building on JONES-19, a small-size image dataset based on The Grammar of Ornament (London, 1857), we evaluate the discriminative performance of Convolutional Neural Networks (CNNs) in two model training strategies: (a) ImageNet pretraining for domain-general "visual common sense," and (b) learning from scratch on the design data in JONES-19. We find that while domain-general priors improve discriminative performance, learning from scratch augmented with repeated local sampling (multi-crop) effectively recovers these gains. For highly structured design data, local design-driven representations provide sufficient foundation for learning, challenging a reliance on massive general-purpose pretraining. These findings suggest that in specialized design domains, careful curation of smaller high-quality datasets that capture empirical and formal design principles may prove more effective and informative on the nature of a particular design domain than prioritizing large-scale data collection.
