Open-World Semi-Supervised Learning
Open-World Semi-Supervised Learning
复制标题
DOI：
--
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Kaidi Cao;Maria Brbic;J. Leskovec
中科院分区：
文献类型：
--
作者：
Kaidi Cao;Maria Brbic;J. Leskovec
在现实环境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，在野外数据中，属于新类的实例可能在测试时出现。在这里，我们引入了一种新颖的开放世界半监督学习设置，该设置形式化了新类可能出现在未标记的测试数据中的概念。在这个新颖的设置中，目标是解决标记和未标记数据之间的类分布不匹配，在测试时，每个输入实例要么需要被分类到一个现有的类中，要么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，这是一种端到端深度学习方法，它引入了不确定性自适应边际机制，以避免由于学习已知类的判别特征比学习新类更快而导致对已知类的偏见。通过这种方式，ORCA减少了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始终优于其他基线，在图像分类数据集上实现了25%的改进，在ImageNet数据集的新类别上实现了96%的改进。
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.