Data, Architecture, or Losses: What Contributes Most to Multimodal Transformer Success?

In this work, we examine what aspects of multimodal transformers – attention, losses, and pretraining data – are important in their success at multimodal pretraining. We find that Multimodal attention, where both language and image transformers attend to each other, is crucial for these models’ success. Models with other types of attention (even with more depth or parameters) fail to achieve comparable results to shallower and smaller models with multimodal attention....

Submit