Closing the Modality Gap via Simplex-Constrained Representations
While multimodal contrastive models like CLIP and CLAP successfully learn shared representations, their embeddings typically exhibit a persistent \emph{modality gap}. We propose addressing this separation through a purely geometric approach: changing the embedding domain from the unit sphere, $S^{d-1}$, to the probabil...
Shubham Gupta, Siva Reddy, Perouz Taslakian et al.
· Interspeech · 0 citations