One does not fit all! On the Complementarity of Vision Encoders for Vision and Language Tasks

Published in CoRR, 2022

Recommended citation: Gregor Geigle, Chen Liu, Jonas Pfeiffer, Iryna Gurevych, "One does not fit all! On the Complementarity of Vision Encoders for Vision and Language Tasks." CoRR, 2022. https://doi.org/10.48550/arXiv.2210.06379