主密钥滤波器假设：深层滤波器是通用的
The Master Key Filters Hypothesis: Deep Filters Are General
AI总结：
本文提出“主密钥滤波器假设”，通过跨领域迁移学习实验证明DS-CNN的深层滤波器保持通用性而非专门化，揭示了空间特征在所有层和架构中的泛化本质，为迁移学习和模型设计提供了新见解。
摘要：
本文挑战了卷积神经网络（CNN）滤波器在深层中变得日益专门化的普遍观点。受在ImageNet上训练的深度可分离CNN（DS-CNN）中可聚类重复模式的最新观察启发，我们将此研究扩展到不同领域和数据集。对DS-CNN的分析表明，深层滤波器保持通用性，与预期的向类特定滤波器的转变相矛盾。我们通过迁移学习实验证明了这些滤波器的泛化能力，表明来自在不同数据集上训练的模型的冻结滤波器表现良好，并且当源自更大数据集时可进一步提升。我们的发现表明，深度可分离卷积学习的空间特征在所有层、领域和架构中保持通用。本研究为神经网络中泛化的本质提供了新见解，特别是在DS-CNN中，并对迁移学习和模型设计具有重要意义。
英文摘要：
This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clusterable repeating patterns in depthwise separable CNNs (DS-CNNs) trained on ImageNet, we extend this investigation across various domains and datasets. Our analysis of DS-CNNs reveals that deep filters maintain generality, contradicting the expected transition to class-specific filters. We demonstrate the generalizability of these filters through transfer learning experiments, showing that frozen filters from models trained on different datasets perform well and can be further improved when sourced from larger datasets. Our findings indicate that spatial features learned by depthwise separable convolutions remain generic across all layers, domains, and architectures. This research provides new insights into the nature of generalization in neural networks, particularly in DS-CNNs, and has significant implications for transfer learning and model design.
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。
