提出新模型PoNG，提升视觉推理任务的泛化能力。
Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
- 采用分组卷积与归一化并行结构设计
- 在多个抽象视觉推理任务上超越现有方法
- 适合研究模型泛化与视觉推理的学者
抽象视觉推理（AVR）领域包含多种基于类比的任务，用于研究模型的泛化能力。近年来，该领域在同分布（i.i.d.）场景下取得显著进展，即模型在相同数据分布上训练与评估。然而，面对新测试分布的跨分布（o.o.d.）场景，即使最新模型仍面临挑战。为提升AVR任务中的泛化性能，本文提出路径归一化分组卷积模型（PoNG），一种融合分组卷积、归一化和并行结构的新型神经网络架构。我们在涵盖瑞文渐进矩阵（Raven's Progressive Matrices）及合成与真实图像的视觉类比问题等广泛AVR基准上进行了实验，结果表明所提模型具备出色的泛化能力，在多个设置中优于现有文献方法。
原文摘要 · Abstract (English)
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in the field, particularly in i.i.d. scenarios, in which models are trained and evaluated on the same data distributions. Nevertheless, o.o.d. setups that assess model generalization to new test distributions remain challenging even for the most recent models. To advance generalization in AVR tasks, we present the Pathways of Normalized Group Convolution model (PoNG), a novel neural architecture that features group convolution, normalization, and a parallel design. We consider a wide set of AVR benchmarks, including Raven's Progressive Matrices and visual analogy problems with both synthetic and real-world images. The experiments demonstrate strong generalization capabilities of the proposed model, which in several settings outperforms the existing literature methods.
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。