论文-《GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering》

最新推荐文章于 2026-04-22 09:39:01 发布

原创

最新推荐文章于 2026-04-22 09:39:01 发布 · 2.3k 阅读

标签

#GQA #VQA #数据集 #论文

GQA数据集旨在解决现有VQA数据集的局限性，提供真实世界的视觉推理和合成问题回答。通过2200万个问题，利用Visual Genome生成具有功能程序的问题，以控制答案分布并减少偏差。数据集附带新的评估指标，分析表明，尽管最先进的模型达到54.1%的准确率，但人类表现高达89.3%，揭示了改进的空间。

论文下载

摘要（Abstract）：

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings ofprevious VQA datasets. We have developed a strong and robust question engine that leverages Visual Genome scene graph structures to create 22M diverse reasoning questions, which all come with functional programs that represent their semantics. We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases. Accompanying the dataset is a suite ofnew metrics that evaluate essential qualities such as consistency, grounding and plausibility. A careful analysis is performed for baselines as well as state-of-the-art models, providing fine-grained results for different question types and topologies. Whereas a blind LSTM obtains a mere 42.1%, and strong VQA models achieve 54.1%, human performance tops at 89.3%, offering ample opportunity for new research to explore. We hope GQA will provide an enabling resource for the next generation ofmodels with enhanced robustness, improved consistency, and deeper semantic understanding ofvision and language.

这里介绍了一个新的数据集GQA，用于对真实图像进行推理和对合成问题进行回答，来解决之前VQA数据集存在的缺陷。作者开发了一个问题引擎，利用Visual Genome数据集的场景图来构建2200万个不同的推理问题，问题都带有一个功能程序