SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
Bo Han, Masashi Sugiyama(Tokyo University of Science), Ivor W. Tsang(Agency for Science, Technology and Research), Xingrui Yu(China University of Petroleum, Beijing), Miao Xu(The University of Queensland), Quanming Yao(Tsinghua University), Gang Niu(Xi'an Jiaotong University)
Cited by 64
Related Papers
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
|Neural Information Processing Systems|2018|1.2k
Core Vector Machines: Fast SVM Training on Very Large Data Sets
|Unknown|2005|951
Domain Transfer Multiple Kernel Learning
|IEEE Transactions on Pattern Analysis and Machine Intelligence|2011|574
Flexible Manifold Embedding: A Framework for Semi-Supervised and Unsupervised Dimension Reduction
|IEEE Transactions on Image Processing|2010|513
Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation
|IEEE Transactions on Pattern Analysis and Machine Intelligence|2013|467