论文标题
带有内核网络的开放世界类发现
Open-World Class Discovery with Kernel Networks
论文作者
论文摘要
我们研究一个开放世界的类发现问题，在该问题中，鉴于旧课程的标记培训样本，我们需要从未标记的测试样本中发现新课程。解决此范式有两个关键的挑战：（a）将知识从旧类转移到新班级，以及（b）将从新课程学到的知识纳入原始模型。我们建议使用扩展（CD-knet-exp）（一个深度学习框架）进行类发现内核网络，该框架利用Hilbert Schmidt独立标准以系统的方式将监督和无监督的信息桥接在一起，以便从旧类中熟悉的知识适当地蒸馏出来，以发现新的类别。与竞争方法相比，CD-knet-Exp在三个公开可用的基准数据集和一个具有挑战性的现实射频指纹数据集上显示出卓越的性能。
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.
