Bongard-HOI：面向人-物交互的少样本视觉推理基准测试
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
AI总结：
本文提出Bongard-HOI基准，通过少样本和上下文相关推理评估人-物交互的组合学习能力，并揭示现有模型与人类水平之间的显著差距。
摘要：
当今的视觉模式识别模型与人类水平的视觉认知之间仍存在显著差距，尤其是在少样本学习和新概念的组合推理方面。我们引入了Bongard-HOI，这是一个新的视觉推理基准，专注于从自然图像中对人-物交互（HOIs）进行组合学习。它受到经典Bongard问题（BPs）的两个理想特性的启发：1）少样本概念学习，以及2）上下文相关推理。我们精心构建了带有困难负样本的少样本实例，其中正图像和负图像仅在动作标签上存在差异，这使得仅仅识别物体类别不足以完成我们的基准测试。我们还设计了多个测试集，以系统地研究视觉学习模型的泛化能力，在这些测试集中，我们改变少样本实例的训练集和测试集之间HOI概念的重叠程度，从部分重叠到完全不重叠。Bongard-HOI对当今的视觉识别模型构成了重大挑战。最先进的HOI检测模型在少样本二分类预测上仅达到62%的准确率，而即使是MTurk上的业余人类测试者也达到了91%的准确率。通过Bongard-HOI基准，我们希望进一步推进视觉推理方面的研究工作，尤其是在整体感知-推理系统和更好的表示学习方面。
英文摘要：
A significant gap remains between today's visual pattern recognition models and human-level visual cognition especially when it comes to few-shot learning and compositional reasoning of novel concepts. We introduce Bongard-HOI, a new visual reasoning benchmark that focuses on compositional learning of human-object interactions (HOIs) from natural images. It is inspired by two desirable characteristics from the classical Bongard problems (BPs): 1) few-shot concept learning, and 2) context-dependent reasoning. We carefully curate the few-shot instances with hard negatives, where positive and negative images only disagree on action labels, making mere recognition of object categories insufficient to complete our benchmarks. We also design multiple test sets to systematically study the generalization of visual learning models, where we vary the overlap of the HOI concepts between the training and test sets of few-shot instances, from partial to no overlaps. Bongard-HOI presents a substantial challenge to today's visual recognition models. The state-of-the-art HOI detection model achieves only 62% accuracy on few-shot binary prediction while even amateur human testers on MTurk have 91% accuracy. With the Bongard-HOI benchmark, we hope to further advance research efforts in visual reasoning, especially in holistic perception-reasoning systems and better representation learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
