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 2007.12368cs.CV
收藏

跨领域的自监督学习

Self-Supervised Learning Across Domains

Politecnico di Torino(都灵理工大学);Italian Institute of Technology(意大利理工学院);University of Rome Sapienza(罗马第一大学);Huawei AI Theory(华为AI理论实验室)

Silvia Bucci, Antonio D'Innocente, Yujun Liao, Fabio Maria Carlucci, Barbara Caputo, Tatiana Tommasi

摘要:

人类的适应性主要依赖于学习和融合来自监督和非监督任务的知识:父母指出一些重要的概念,但孩子们自己填补空白。这是特别有效的,因为监督学习永远不会是穷尽的,因此自主学习允许发现有助于概括的不变性和不变性。在本文中,我们提出将类似的方法应用于跨领域的对象识别问题:我们的模型以监督的方式学习语义标签,并通过从相同图像上的自监督信号学习来扩展对数据的理解。这个次要任务帮助网络专注于物体形状,学习空间方向和部分相关性等概念,同时充当多个视觉域分类任务的正则化器。大量的实验证实了我们的直觉,并表明我们的多任务方法相结合的监督和自我监督的知识显示出竞争力的结果,更复杂的领域泛化和适应的解决方案。它也证明了其潜力,在新的和具有挑战性的预测和部分领域自适应的情况下。

英文摘要:

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to focus on object shapes, learning concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task over multiple visual domains. Extensive experiments confirm our intuition and show that our multi-task method combining supervised and self-supervised knowledge shows competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation 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。

↑