Combinatorial Inference Against Label Noise
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)(2019)
摘要
Label noise is one of the critical sources that degrade generalization performance of deep neural networks significantly. To handle the label noise issue in a principled way, we propose a unique classification framework of constructing multiple models in heterogeneous coarse-grained meta-class spaces and making joint inference of the trained models for the final predictions in the original (base) class space. Our approach reduces noise level by simply constructing meta-classes and improves accuracy via combinatorial inferences over multiple constituent classifiers. Since the proposed framework has distinct and complementary properties for the given problem, we can even incorporate additional off-the-shelf learning algorithms to improve accuracy further. We also introduce techniques to organize multiple heterogeneous meta-class sets using k-means clustering and identify a desirable subset leading to learn compact models. Our extensive experiments demonstrate outstanding performance in terms of accuracy and efficiency compared to the state-of-the-art methods under various synthetic noise configurations and in a real-world noisy dataset.
更多查看译文
关键词
outstanding performance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要