Open-World Class Discovery with Kernel Networks
Open-World Class Discovery with Kernel Networks
复制标题
DOI：
10.1109/icdm50108.2020.00072
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Zifeng Wang;Batool Salehi;Andrey Gritsenko;K. Chowdhury;Stratis Ioannidis;Jennifer G. Dy
中科院分区：
文献类型：
--
作者：
Zifeng Wang;Batool Salehi;Andrey Gritsenko;K. Chowdhury;Stratis Ioannidis;Jennifer G. Dy
我们研究了一个开放世界类发现问题，在这个问题中，给定来自旧类的标记训练样本，我们需要从未标记的测试样本中发现新类。解决这一范式有两个关键挑战：（a）将知识从旧类转移到新类，（B）将从新类学到的知识重新纳入原始模型。我们提出了扩展类发现核网络（CD-KNet-Exp），这是一个深度学习框架，它利用希尔伯特施密特独立性准则以系统的方式将监督和非监督信息连接在一起，以便从旧类中学习到的知识被适当地提取以发现新类。与竞争方法相比，CD-KNet-Exp在三个公开的基准数据集和一个具有挑战性的真实世界射频指纹数据集上显示出上级性能。
We study an Open-World Class Discovery problem in which, given labeled training samples from old classes, we need to discover new classes from unlabeled test samples. There are two critical challenges to addressing this paradigm: (a) transferring knowledge from old to new classes, and (b) incorporating knowledge learned from new classes back to the original model. We propose Class Discovery Kernel Network with Expansion (CD-KNet-Exp), a deep learning framework, which utilizes the Hilbert Schmidt Independence Criterion to bridge supervised and unsupervised information together in a systematic way, such that the learned knowledge from old classes is distilled appropriately for discovering new classes. Compared to competing methods, CD-KNet-Exp shows superior performance on three publicly available benchmark datasets and a challenging real-world radio frequency fingerprinting dataset.