论文标题
用标签噪声学习的拓扑过滤器
A Topological Filter for Learning with Label Noise
论文作者
论文摘要
嘈杂的标签可能会损害深度神经网络的性能。为了解决这个问题，在本文中，我们提出了一种过滤标签噪声的新方法。与大多数依靠嘈杂分类器的后验概率的现有方法不同，我们专注于潜在代表空间中数据的更丰富的空间行为。通过利用数据的高阶拓扑信息，我们能够收集大多数干净的数据并训练高质量的模型。从理论上讲，我们证明这种拓扑方法可以保证以很高的可能性收集干净的数据。经验结果表明，我们的方法的表现优于最先进的方法，并且在广泛的噪声类型和水平方面具有鲁棒性。
Noisy labels can impair the performance of deep neural networks. To tackle this problem, in this paper, we propose a new method for filtering label noise. Unlike most existing methods relying on the posterior probability of a noisy classifier, we focus on the much richer spatial behavior of data in the latent representational space. By leveraging the high-order topological information of data, we are able to collect most of the clean data and train a high-quality model. Theoretically we prove that this topological approach is guaranteed to collect the clean data with high probability. Empirical results show that our method outperforms the state-of-the-arts and is robust to a broad spectrum of noise types and levels.
