Conference
Open access
Sep 2026
SPACE: Semantic Projection and Alignment of Clip Embeddings for Domain Adaptation
SPACE is introduced, a method that exploits the semantic structure of CLIP's vision-language space for domain adaptation by applying Singular Value Decomposition to CLIP embeddings of class descriptions, yielding an orthogonal basis that captures semantic relationships among categories.
J. R. Manesco, D. Jodas, Douglas Rodrigues et al.
· International Conference on... · 0 citations