On transfer learning using a MAC model variant

Understand

We introduce a variant of the MAC model (Hudson and Manning, ICLR 2018) with a simplified set of equations that achieves comparable accuracy, while training faster.

• We evaluate both models on CLEVR and CoGenT, and show that, transfer learning with fine-tuning results in a 15 point increase in accuracy, matching the state of the art.
• Finally, in contrast, we demonstrate that improper fine-tuning can actually reduce a model's accuracy as well.