通过可微聚类提升少样本学习与域适应性能
SuperCM: Improving Semi-Supervised Learning and Domain Adaptation through differentiable clustering
- 引入可微聚类模块，显式利用标注数据计算聚类中心
- 在低监督场景下显著提升模型性能，优于现有方法
- 既可独立使用，也可作为正则项增强已有模型
半监督学习（SSL）和无监督域适应（UDA）通过利用标注和未标注数据来提升模型性能。聚类假设表明，在高维空间中属于同一簇的数据点应被分配到相同类别。近期工作通过不同训练机制隐式强化该假设。本文提出一种新方法：显式引入可微聚类模块，并利用有标签数据计算聚类中心。通过大量实验验证了该端到端训练策略在SSL和UDA中的有效性，尤其在低监督条件下表现突出，既可作为独立模型，也可作为现有方法的正则化器。
原文摘要 · Abstract (English)
Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited supervision and states that data points belonging to the same cluster in a high-dimensional space should be assigned to the same category. Recent works have utilized different training mechanisms to implicitly enforce this assumption for the SSL and UDA. In this work, we take a different approach by explicitly involving a differentiable clustering module which is extended to leverage the supervised data to compute its centroids. We demonstrate the effectiveness of our straightforward end-to-end training strategy for SSL and UDA over extensive experiments and highlight its benefits, especially in low supervision regimes, both as a standalone model and as a regularizer for existing approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。