Dilated densenets for relational reasoning
arXiv preprint arXiv:1811.00410, 2018•arxiv.org
Despite their impressive performance in many tasks, deep neural networks often struggle at
relational reasoning. This has recently been remedied with the introduction of a plug-in
relational module that considers relations between pairs of objects. Unfortunately, this is
combinatorially expensive. In this extended abstract, we show that a DenseNet incorporating
dilated convolutions excels at relational reasoning on the Sort-of-CLEVR dataset, allowing
us to forgo this relational module and its associated expense.
relational reasoning. This has recently been remedied with the introduction of a plug-in
relational module that considers relations between pairs of objects. Unfortunately, this is
combinatorially expensive. In this extended abstract, we show that a DenseNet incorporating
dilated convolutions excels at relational reasoning on the Sort-of-CLEVR dataset, allowing
us to forgo this relational module and its associated expense.
Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. This has recently been remedied with the introduction of a plug-in relational module that considers relations between pairs of objects. Unfortunately, this is combinatorially expensive. In this extended abstract, we show that a DenseNet incorporating dilated convolutions excels at relational reasoning on the Sort-of-CLEVR dataset, allowing us to forgo this relational module and its associated expense.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果