IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning

arXiv: Artificial Intelligence(2018)

引用 51|浏览161
暂无评分
摘要
In order to reach human performance on complexvisual tasks, artificial systems need to incorporate a sig-nificant amount of understanding of the world in termsof macroscopic objects, movements, forces, etc. Inspiredby work on intuitive physics in infants, we propose anevaluation benchmark which diagnoses how much a givensystem understands about physics by testing whether itcan tell apart well matched videos of possible versusimpossible events constructed with a game engine. Thetest requires systems to compute a physical plausibilityscore over an entire video. It is free of bias and cantest a range of basic physical reasoning concepts. Wethen describe two Deep Neural Networks systems aimedat learning intuitive physics in an unsupervised way,using only physically possible videos. The systems aretrained with a future semantic mask prediction objectiveand tested on the possible versus impossible discrimi-nation task. The analysis of their results compared tohuman data gives novel insights in the potentials andlimitations of next frame prediction architectures.
更多
查看译文
关键词
benchmark,physics,framework
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