OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning

CoRR(2023)

引用 0|浏览20
暂无评分
摘要
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios. Such capacity is not yet attained for machine learning systems. In this work, in the context of visual reasoning, we show how modularity can be leveraged to derive a compositional data augmentation framework inspired by imagination. Our method, denoted Object-centric Compositional Neural Module Network (OC-NMN), decomposes visual generative reasoning tasks into a series of primitives applied to objects without using a domain-specific language. We show that our modular architectural choices can be used to generate new training tasks that lead to better out-of-distribution generalization. We compare our model to existing and new baselines in proposed visual reasoning benchmark that consists of applying arithmetic operations to MNIST digits.
更多
查看译文
关键词
compositional,reasoning,oc-nmn,object-centric
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