Publication
(alpha)ILP: thinking visual scenes as differentiable logic programs
Hikaru Shindo; Viktor Pfanschilling; Devendra Singh Dhami; Kristian Kersting
In: Machine Learning, Vol. 112, No. 5, Pages 1465-1497, Springer, 2023.
Abstract
Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of visual scenes, such as Kandinsky patterns and Bongard problems. To overcome these limitations, we introduce , a novel differentiable inductive logic programming framework that learns to represent scenes as logic programs—intuitively, logical atoms correspond to objects, attributes, and relations, and clauses encode high-level scene information. ILP has an end-to-end reasoning architecture from visual inputs. Using it, ILP performs differentiable inductive logic programming on complex visual scenes, i.e., the logical rules are learned by gradient descent. Our extensive experiments on and benchmarks demonstrate the accuracy and efficiency of in learning complex visual-logical concepts.