DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs

TL;DR

The paper introduces DIRCR, a novel visual reasoning model that combines local and global inference paths with contrastive learning to improve rule understanding and generalization on RAVEN datasets.

Contribution

It proposes a dual-inference reasoning framework with rule-contrastive learning, effectively integrating local and global reasoning for visual question answering.

Findings

Significantly improves reasoning robustness on RAVEN datasets.

Enhances feature separability through contrastive learning.

Achieves better generalization compared to existing methods.

Abstract

Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermediate feature constraints, leading to incomplete rule capture and entangled representations. To address these issues, we propose the Dual-Inference Rule-Contrastive Reasoning (DIRCR) model. Its core component, the Dual-Inference Reasoning Module, combines a local path for row-wise analogical reasoning and a global path for holistic inference, integrated via a gated attention mechanism. Additionally, a Rule-Contrastive Learning Module introduces pseudo-labels to construct positive and negative rule samples, applying contrastive learning to enhance feature separability and promote abstract, transferable rule learning. Experimental results on three RAVEN datasets demonstrate that DIRCR significantly enhances reasoning robustness and generalization. Codes are available at https://github.com/csZack-Zhang/DIRCR.