Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices

by   Nicholas Quek Wei Kiat, et al.

Abstract reasoning is a key indicator of intelligence. The ability to hypothesise, develop abstract concepts based on concrete observations and apply this hypothesis to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent machines with abstract reasoning capabilities revolves around the Raven's Progressive Matrices (RPM), a multiple-choice visual puzzle where one must identify the missing component which completes the pattern. There have been many breakthroughs in supervised approaches to solving RPM in recent years. However, since this process requires external assistance, we cannot claim that machines have achieved reasoning ability comparable to humans. Namely, when the RPM rule that relations can only exist row/column-wise is properly introduced, humans can solve RPM problems without supervision or prior experience. In this paper, we introduce a pairwise relations discriminator (PRD), a technique to develop unsupervised models with sufficient reasoning abilities to tackle an RPM problem. PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem. We can identify the optimal candidate by adapting the application of PRD on the RPM problem. The previous state-of-the-art approach "mcpt" in this domain achieved 28.5 accuracy on the RAVEN dataset "drt", a standard dataset for computational work on RPM. Our approach, the PRD, establishes a new state-of-the-art benchmark with an accuracy of 50.74 improvement and a step forward in equipping machines with abstract reasoning.


page 1

page 2

page 3

page 4


Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices

Abstract visual reasoning (AVR) domain encompasses problems solving whic...

DAReN: A Collaborative Approach Towards Reasoning And Disentangling

Computational learning approaches to solving visual reasoning tests, suc...

Multi-Label Contrastive Learning for Abstract Visual Reasoning

For a long time the ability to solve abstract reasoning tasks was consid...

Effective Abstract Reasoning with Dual-Contrast Network

As a step towards improving the abstract reasoning capability of machine...

SAViR-T: Spatially Attentive Visual Reasoning with Transformers

We present a novel computational model, "SAViR-T", for the family of vis...

Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

Raven's Progressive Matrices are a benchmark originally designed to test...

Hierarchical Rule Induction Network for Abstract Visual Reasoning

Abstract reasoning refers to the ability to analyze information, discove...

Please sign up or login with your details

Forgot password? Click here to reset