Subdomain-aware representation compression for pretrained image embeddings

Abstract: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.

Machine Learning (cs.LG)

arXiv:2609.20213 [cs.LG]

(or arXiv:2609.20213v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.20213 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.