Open-World Class Discovery with Kernel Networks

Autor:	Wang, Zifeng, Salehi, Batool, Gritsenko, Andrey, Chowdhury, Kaushik, Ioannidis, Stratis, Dy, Jennifer
Rok vydání:	2020
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to the IEEE International Conference on Data Mining 2020 (ICDM'20); Best paper candidate
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2012.06957 Zobrazit plný text záznamu View this record from Arxiv