#machine learning
Oct 2025
Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
KME-CLIP is proposed, which leverages this structure through the inner product in a reproducing kernel Hilbert space (RKHS) and theoretically proves that the KME-CLIP similarity can bring the contrastive loss arbitrarily close to its optimal value, which is attained by PMI, as the size of the point set grows.
Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida et al.
· arXiv.org · 2 citations