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 2108.01621cs.LGcs.CVeess.IV
收藏

基于梯度手术的领域泛化

Domain Generalization via Gradient Surgery

CONICET(国家科学技术研究委员会);UNL(国立滨海大学)

Lucas Mansilla, Rodrigo Echeveste, Diego H. Milone, Enzo Ferrante

摘要:

在实际应用中,机器学习模型经常面临训练域和测试域之间的数据分布发生变化的场景。当目标是对不同于训练时看到的分布进行预测时,我们会遇到领域泛化问题。解决此问题的方法使用来自多个源域的数据学习模型,然后将此模型应用于看不见的目标域。我们的假设是,当使用多个域进行训练时,每个小批中的冲突梯度包含特定于各个域的信息,这些信息与其他域(包括测试域)无关。如果保持不变,这种分歧可能会降低泛化性能。在这项工作中,我们的特点是出现在域转移的情况下,并设计新的梯度协议的基础上梯度手术,以减轻其影响的战略冲突的梯度。我们在三个多域数据集的图像分类任务中验证了我们的方法,显示了所提出的一致性策略在增强域转移场景中深度学习模型的泛化能力方面的价值。

英文摘要:

In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. When the aim is to make predictions on distributions different from those seen at training, we incur in a domain generalization problem. Methods to address this issue learn a model using data from multiple source domains, and then apply this model to the unseen target domain. Our hypothesis is that when training with multiple domains, conflicting gradients within each mini-batch contain information specific to the individual domains which is irrelevant to the others, including the test domain. If left untouched, such disagreement may degrade generalization performance. In this work, we characterize the conflicting gradients emerging in domain shift scenarios and devise novel gradient agreement strategies based on gradient surgery to alleviate their effect. We validate our approach in image classification tasks with three multi-domain datasets, showing the value of the proposed agreement strategy in enhancing the generalization capability of deep learning models in domain shift scenarios.

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。

↑