Unsupervised semantic aggregation and deformable template matching for semi-supervised learning

科研成果: 期刊稿件会议文章同行评审

20 引用 (Scopus)

摘要

Unlabeled data learning has attracted considerable attention recently. However, it is still elusive to extract the expected high-level semantic feature with mere unsupervised learning. In the meantime, semi-supervised learning (SSL) demonstrates a promising future in leveraging few samples. In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating. Specifically, unsupervised semantic aggregation based on Triplet Mutual Information (T-MI) loss is explored to generate semantic labels for unlabeled data. Then the semantic labels are aligned to the actual class by the supervision of labeled data. Furthermore, a feature pool that stores the labeled samples is dynamically updated to assign proxy labels for unlabeled data, which are used as targets for cross-entropy minimization. Extensive experiments and analysis across four standard semi-supervised learning benchmarks validate that USADTM achieves top performance (e.g., 90.46% accuracy on CIFAR-10 with 40 labels and 95.20% accuracy with 250 labels). The code is released at https://github.com/taohan10200/USADTM.

源语言英语
期刊Advances in Neural Information Processing Systems
2020-December
出版状态已出版 - 2020
活动34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
期限: 6 12月 202012 12月 2020

指纹

探究 'Unsupervised semantic aggregation and deformable template matching for semi-supervised learning' 的科研主题。它们共同构成独一无二的指纹。

引用此