Abstract | ||
---|---|---|
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 modelu0027s accuracy as well. |
Year | Venue | DocType |
---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1811.06529 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vincent Marois | 1 | 0 | 0.34 |
T. S. Jayram | 2 | 1373 | 75.87 |
Vincent Albouy | 3 | 0 | 0.68 |
Tomasz Kornuta | 4 | 55 | 11.95 |
Younes Bouhadjar | 5 | 0 | 1.35 |
Ahmet S. Ozcan | 6 | 0 | 1.69 |