Constellation: Learning relational abstractions over objects for compositional imagination

arxiv(2021)

引用 0|浏览27
暂无评分
摘要
Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning. While there has been exciting progress with slot-based models, which learn to segment scenes into sets of objects, learning configurational properties of entire groups of objects is still under-explored. To address this problem, we introduce Constellation, a network that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities, thus offering a potential basis for abstract relational reasoning. We further show that this basis, along with language association, provides a means to imagine sensory content in new ways. This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures.
更多
查看译文
关键词
compositional imagination,relational abstractions,objects,learning
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