通过双路径推理与规则对比学习，提升视觉推理模型的泛化能力
DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs
- 设计双路径结构：局部行间类比 + 全局整体推理，融合更全面
- 在三个RAVEN数据集上准确率显著提升，增强推理鲁棒性
- 适合研究视觉推理、可解释AI的科研人员使用
抽象视觉推理仍具挑战，现有方法常偏向全局上下文或局部行间关系，难以兼顾二者，且缺乏中间特征约束，导致规则捕捉不全、表征纠缠。为此，我们提出双推理规则对比推理（DIRCR）模型。其核心是双推理模块，结合局部行间类比路径与全局整体推理路径，通过门控注意力机制融合。此外，规则对比学习模块引入伪标签构建正负规则样本，采用对比学习提升特征可分性，促进抽象且可迁移的规则学习。在三个RAVEN数据集上的实验表明，DIRCR显著提升了推理鲁棒性与泛化能力。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。