Learning Abstract Visual Reasoning via Task Decomposition: A Case Study in Raven Progressive Matrices
arxiv(2023)
摘要
Learning to perform abstract reasoning often requires decomposing the task in
question into intermediate subgoals that are not specified upfront, but need to
be autonomously devised by the learner. In Raven Progressive Matrices (RPM),
the task is to choose one of the available answers given a context, where both
the context and answers are composite images featuring multiple objects in
various spatial arrangements. As this high-level goal is the only guidance
available, learning to solve RPMs is challenging. In this study, we propose a
deep learning architecture based on the transformer blueprint which, rather
than directly making the above choice, addresses the subgoal of predicting the
visual properties of individual objects and their arrangements. The
multidimensional predictions obtained in this way are then directly juxtaposed
to choose the answer. We consider a few ways in which the model parses the
visual input into tokens and several regimes of masking parts of the input in
self-supervised training. In experimental assessment, the models not only
outperform state-of-the-art methods but also provide interesting insights and
partial explanations about the inference. The design of the method also makes
it immune to biases that are known to be present in some RPM benchmarks.
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