KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation Yongfei Liu author Chenfei Wu author Shao-Yen Tseng author Vasudev Lal author Xuming He author Nan Duan author 2022-07 text Findings of the Association for Computational Linguistics: NAACL 2022 Marine Carpuat editor Marie-Catherine de Marneffe editor Ivan Vladimir Meza Ruiz editor Association for Computational Linguistics Seattle, United States conference publication liu-etal-2022-kd 10.18653/v1/2022.findings-naacl.119 https://aclanthology.org/2022.findings-naacl.119/ 2022-07 1589 1600