A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels

arXiv:2403.13480v1 Announce Type: new
Abstract: Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet …

abstract arxiv cs.cv cs.ir cs.mm discrimination flexibility framework labels modal performance retrieval semantic success transport type