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 2102.03526cs.LGcs.CV
收藏

开放世界半监督学习

Open-World Semi-Supervised Learning

Stanford University(斯坦福大学)

Kaidi Cao, Maria Brbic, Jure Leskovec

摘要:

在现实世界中应用半监督学习的一个基本限制是假设未标记的测试数据只包含以前在标记的训练数据中遇到的类。然而,这种假设很少适用于野外数据,其中属于新类的实例可能会在测试时出现。在这里,我们介绍了一种新的开放世界的半监督学习设置,形式化的概念,新的类可能会出现在未标记的测试数据。在这种新颖的设置中,目标是解决标记数据和未标记数据之间的类分布不匹配,在测试时,每个输入实例都需要被分类到现有的类中,或者需要初始化一个新的不可见的类。为了解决这个具有挑战性的问题,我们提出了ORCA,一种端到端的深度学习方法,该方法引入了不确定性自适应余量机制,以避免由于学习可见类的判别特征而导致的对可见类的偏见。通过这种方式,ORCA减少了所见的类内方差与新类之间的差距。在图像分类数据集和单细胞注释数据集上的实验表明,ORCA始终优于替代基线,在ImageNet数据集的可见类上实现了25%的改进,在新类上实现了96%的改进。

英文摘要:

A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds for data in-the-wild, where instances belonging to novel classes may appear at testing time. Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data. In this novel setting, the goal is to solve the class distribution mismatch between labeled and unlabeled data, where at the test time every input instance either needs to be classified into one of the existing classes or a new unseen class needs to be initialized. To tackle this challenging problem, we propose ORCA, an end-to-end deep learning approach that introduces uncertainty adaptive margin mechanism to circumvent the bias towards seen classes caused by learning discriminative features for seen classes faster than for the novel classes. In this way, ORCA reduces the gap between intra-class variance of seen with respect to novel classes. Experiments on image classification datasets and a single-cell annotation dataset demonstrate that ORCA consistently outperforms alternative baselines, achieving 25% improvement on seen and 96% improvement on novel classes of the ImageNet 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。

↑