KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning

arXiv:2403.17486v1 Announce Type: new
Abstract: Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results. However, by taking the rest of the batch as negative samples without reviewing when forming contrastive pairs, those studies encountered many suspicious and noisy negative examples, significantly affecting the methods' overall performance. In this work, we propose KDMCSE (Knowledge Distillation Multimodal contrastive learning of Sentence Embeddings), a novel approach that enhances the discrimination and generalizability of multimodal representation and inherits …

abstract angular arxiv cs.cl distillation embedding embeddings examples however knowledge multimodal negative rest results samples studies type work