Training Vision-Language Models with Less Bimodal Supervision.

@inproceedings{segal-2022-training, author = {Elad Segal and Ben Bogin and Jonathan Berant}, editor = {Sebastian Riedel and Eunsol Choi and Andreas Vlachos and James Thorne and Marek Rei and Fabio Petroni}, title = {{Training Vision-Language Models with Less Bimodal Supervision}}, booktitle = {{4th Conference on Automated Knowledge Base Construction, AKBC 2022, London, UK, November 3-5, 2022}}, year = {2022}, url = {https://akbc.ws/2022/papers/21_training_vision_language_model} }