arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15974cs.CV
收藏

领域稳健的VQA,具有不同的数据集和方法,但没有目标标签

Domain-robust VQA with diverse datasets and methods but no target labels

University of Pittsburgh(匹兹堡大学)

Mingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa

摘要:

观察到计算机视觉方法过拟合数据集的具体情况,激发了各种尝试,使对象识别模型对域转移具有鲁棒性。然而,类似的工作领域鲁棒的视觉问答方法是非常有限的。由于额外的复杂性,VQA的领域自适应与对象识别的自适应不同:VQA模型处理多模态输入,方法包含具有不同模块的多个步骤,导致复杂的优化,并且不同数据集中的答案空间差异很大。为了应对这些挑战,我们首先量化了流行的VQA数据集之间的域转移,包括视觉和文本空间。为了解开不同模态所产生的数据集之间的移位,我们还分别在图像和问题域中构建合成移位。其次,我们测试了不同的家庭VQA方法(经典的双流,Transformer,神经符号的方法),这些变化的鲁棒性。第三,我们测试现有的领域自适应方法的适用性,并设计了一个新的桥梁VQA域的差距,调整到特定的VQA模型。为了模拟现实世界的泛化设置,我们专注于无监督的领域自适应和开放式分类任务制定。

英文摘要:

The observation that computer vision methods overfit to dataset specifics has inspired diverse attempts to make object recognition models robust to domain shifts. However, similar work on domain-robust visual question answering methods is very limited. Domain adaptation for VQA differs from adaptation for object recognition due to additional complexity: VQA models handle multimodal inputs, methods contain multiple steps with diverse modules resulting in complex optimization, and answer spaces in different datasets are vastly different. To tackle these challenges, we first quantify domain shifts between popular VQA datasets, in both visual and textual space. To disentangle shifts between datasets arising from different modalities, we also construct synthetic shifts in the image and question domains separately. Second, we test the robustness of different families of VQA methods (classic two-stream, transformer, and neuro-symbolic methods) to these shifts. Third, we test the applicability of existing domain adaptation methods and devise a new one to bridge VQA domain gaps, adjusted to specific VQA models. To emulate the setting of real-world generalization, we focus on unsupervised domain adaptation and the open-ended classification task formulation.

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。

↑