arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.02865cs.CV
收藏

积极寻求和学习实时数据

Actively Seeking and Learning from Live Data

Australian Institute for Machine Learning(澳大利亚机器学习研究所);The University of Adelaide(阿德莱德大学)

Damien Teney, Anton van den Hengel

摘要:

传统机器学习方法的一个关键限制是它们需要训练数据来概括所有要学习的信息。这对于视觉问答方法是一个特殊的问题,视觉问答方法可以被问到几乎任何问题。我们提出的方法是一个步骤,通过搜索测试时所需的信息来克服这一限制。所得到的方法动态地利用来自外部源的数据,例如大量的问题/答案或图像/标题。具体地说,我们为一个简单的VQA模型学习了一组基本权重,这些权重专门适用于给定的问题,并专门为该问题检索到信息。适应过程利用了基于梯度的Meta学习的最新进展以及对高效检索和跨领域自适应的贡献。我们超越了VQA-CP v2基准测试的最新技术水平,并证明了我们的方法在本质上对分布外的测试数据更强大。我们演示了使用MS COCO字幕数据集来支持回答过程的外部非VQA数据的使用。这种方法为与不同数据源接口的开放域VQA系统开辟了一条新途径。

英文摘要:

One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned. This is a particular problem for visual question answering methods, which may be asked questions about virtually anything. The approach we propose is a step toward overcoming this limitation by searching for the information required at test time. The resulting method dynamically utilizes data from an external source, such as a large set of questions/answers or images/captions. Concretely, we learn a set of base weights for a simple VQA model, that are specifically adapted to a given question with the information specifically retrieved for this question. The adaptation process leverages recent advances in gradient-based meta learning and contributions for efficient retrieval and cross-domain adaptation. We surpass the state-of-the-art on the VQA-CP v2 benchmark and demonstrate our approach to be intrinsically more robust to out-of-distribution test data. We demonstrate the use of external non-VQA data using the MS COCO captioning dataset to support the answering process. This approach opens a new avenue for open-domain VQA systems that interface with diverse sources of data.

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。

↑