Domain-specific language alignment of multimodal embeddings towards explainable predictions
Multimodal data are commonly fused into latent representations that improve downstream task performance but are not interpretable, limiting their application in domains that require explainable model decisions. Vision-language alignment has made image embeddings interpretable through language, but requires vast image-c...
Gabriele Tijunaityte, T. L. van der Plas, M. Belaid et al.
· 0 citations