Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction
This work addresses visual reasoning challenges for AI systems, particularly in real-world applications like video prediction, though it appears incremental as it builds on existing two-stage approaches.
The paper tackles the Raven's Progressive Matrices (RPM) problem by proposing a two-stage rule-induction visual reasoner (TRIVR) that separates visual recognition and logical reasoning, achieving significant and consistent performance gains over state-of-the-art models on various RPM-like datasets.
Raven's Progressive Matrices (RPMs) are frequently used in evaluating human's visual reasoning ability. Researchers have made considerable efforts in developing systems to automatically solve the RPM problem, often through a black-box end-to-end convolutional neural network for both visual recognition and logical reasoning tasks. Based on the two intrinsic natures of RPM problem, visual recognition and logical reasoning, we propose a Two-stage Rule-Induction Visual Reasoner (TRIVR), which consists of a perception module and a reasoning module, to tackle the challenges of real-world visual recognition and subsequent logical reasoning tasks, respectively. For the reasoning module, we further propose a "2+1" formulation that models human's thinking in solving RPMs and significantly reduces the model complexity. It derives a reasoning rule from each RPM sample, which is not feasible for existing methods. As a result, the proposed reasoning module is capable of yielding a set of reasoning rules modeling human in solving the RPM problems. To validate the proposed method on real-world applications, an RPM-like Video Prediction (RVP) dataset is constructed, where visual reasoning is conducted on RPMs constructed using real-world video frames. Experimental results on various RPM-like datasets demonstrate that the proposed TRIVR achieves a significant and consistent performance gain compared with the state-of-the-art models.