Paper ID: 2403.03452

D4C Glove-train: Solving the RPM and Bongard-logo Problem by Circumscribing and Building Distribution for Concepts

Ruizhuo Song, Beiming Yuan

This paper achieves noteworthy progress in the realm of abstract reasoning, particularly in addressing Raven's Progressive Matrices (RPM) and Bongard-Logo challenges. Initially, we introduce Lico-Net, a novel baseline model that resolves RPM problems with remarkable accuracy. Leveraging this foundation, we advance with the D3C approach, which advocates representing the underlying concepts in abstract reasoning problems through distributions. This perspective enhances the performance of both Lico-Net and a baseline model excelling in Bongard-Logo tasks. To bolster the computational efficiency of D3C, we present the D3C-cos variant, offering a streamlined solution. Furthermore, we propose the D2C method, redefining concept boundaries within these domains and bridging the divide between high-level abstractions and their lower-dimensional counterparts. Finally, we extend our methodology to D4C, employing adversarial techniques to refine concept boundaries further and demonstrate substantial improvements in both RPM and Bongard-Logo challenges. Overall, our contributions present a fresh outlook and practical advancements in the field of abstract reasoning.

Submitted: Mar 6, 2024