Abstract: Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models ...
Abstract: Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback