AI 中文总结
本文研究利用PCA和LDA等降维技术对预训练图像嵌入进行子域感知压缩，在提升空间与计算效率的同时提高准确率，并验证了压缩表示的迁移学习能力。
AI 中文摘要
降维是一种众所周知的技术，用于提高空间效率，通常对整个数据集统一应用。本文研究了使用降维技术进行子域表示压缩的可能性。我们在图像领域探索了诸如主成分分析（PCA）和线性判别分析（LDA）等标准技术。结果不仅展示了在空间和计算复杂度方面的预期改进，这对边缘设备机器学习应用至关重要，而且相比直接使用完整嵌入过程，还显示了准确率的提升。一个可能的解释是，降维有效地提取了子域特征。我们还进行了实验，以展示使用压缩表示的迁移学习能力。
英文摘要
Dimensionality reduction is a well-known technique for improving space efficiency, typically applied uniformly across an entire dataset. This paper investigates the possibilities of using dimensionality reduction techniques for subdomain representation compression. We explore standard techniques such as Principal Component Analysis (PCA) and Linear discriminant analysis (LDA) in image domains. The results not only demonstrate the expected improvements in space and computation complexity crucial for edge-device ML applications but also show improvements in accuracy over direct full-embedding procedure. One possible explanation is that dimensionality reduction effectively extracts subdomain features. We also performed experiments to demonstrate transfer learning capabilities using the compressed representations.
CommentsAppeared in JCSSE2026
