arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1902.05660cs.CV
收藏

鲁棒可视问答的周期一致性

Cycle-Consistency for Robust Visual Question Answering

Facebook AI Research(脸书人工智能研究院);Georgia Institute of Technology(佐治亚理工学院)

Meet Shah, Xinlei Chen, Marcus Rohrbach, Devi Parikh

摘要:

尽管这些年来在视觉问答方面取得了显著的进步,但今天的VQA模型的鲁棒性还有很多需要改进的地方。我们介绍了一个新的评估协议和相关的数据集(VQA-Rephrasings),并表明,最先进的VQA模型是出了名的脆弱的语言变化的问题。VQA-Rephrasings包含3个人工提供的Rephrasings,涉及VQA v2.0验证数据集的40 k个图像的40 k个问题。作为提高VQA模型鲁棒性的一步,我们提出了一个利用周期一致性的模型不可知框架。具体来说,我们训练模型,使其不仅回答问题,而且还生成以答案为条件的问题,使得针对所生成的问题预测的答案与原始问题的基本事实答案相同。在不使用额外注释的情况下,我们表明,当在VQA-Rephrasings数据集上进行评估时,我们的方法对语言变化的鲁棒性比最先进的VQA模型要高得多。此外,在具有挑战性的VQA v2.0数据集上,我们的方法在标准VQA和可视化问题生成任务上的表现优于最先进的方法。

英文摘要:

Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions. VQA-Rephrasings contains 3 human-provided rephrasings for 40k questions spanning 40k images from the VQA v2.0 validation dataset. As a step towards improving robustness of VQA models, we propose a model-agnostic framework that exploits cycle consistency. Specifically, we train a model to not only answer a question, but also generate a question conditioned on the answer, such that the answer predicted for the generated question is the same as the ground truth answer to the original question. Without the use of additional annotations, we show that our approach is significantly more robust to linguistic variations than state-of-the-art VQA models, when evaluated on the VQA-Rephrasings dataset. In addition, our approach outperforms state-of-the-art approaches on the standard VQA and Visual Question Generation tasks on the challenging VQA v2.0 dataset.

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。

↑