Attribute Diversity Determines the Systematicity Gap in VQA
arxiv(2023)
摘要
The degree to which neural networks can generalize to new combinations of
familiar concepts, and the conditions under which they are able to do so, has
long been an open question. In this work, we study the systematicity gap in
visual question answering: the performance difference between reasoning on
previously seen and unseen combinations of object attributes. To test, we
introduce a novel diagnostic dataset, CLEVR-HOPE. We find that while increased
quantity of training data does not reduce the systematicity gap, increased
training data diversity of the attributes in the unseen combination does. In
all, our experiments suggest that the more distinct attribute type combinations
are seen during training, the more systematic we can expect the resulting model
to be.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要