Adding representation-level and structure-aware distillation from single-modal teachers to cross-modal contrastive training improves both cross-modal and single-modal retrieval under modality imbalance.
Deep relation embedding for cross-modal retrieval,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation
Adding representation-level and structure-aware distillation from single-modal teachers to cross-modal contrastive training improves both cross-modal and single-modal retrieval under modality imbalance.