Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking

arXiv:2404.08535v1 Announce Type: cross
Abstract: Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal requirement for manual annotations. However, popular contrastive frameworks typically learn from binary relevance, making them ineffective at incorporating direct fine-grained rankings. In this paper, we curate a large-scale dataset featuring detailed relevance scores for each query-document pair to facilitate future research and evaluation. Subsequently, we propose Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking (GCL), which is designed to learn from fine-grained …

abstract adoption annotations arxiv binary cs.cv cs.ir cs.lg dataset fine-grained frameworks generalized however learn making modal multi-modal paper popular ranking rankings retrieval scale tasks them type