arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2111.04239cs.LG
收藏

学习纠正带噪声标签的鲁棒学习

Learning to Rectify for Robust Learning with Noisy Labels

Shandong University(山东大学)

Haoliang Sun, Chenhui Guo, Qi Wei, Zhongyi Han, Yilong Yin

摘要:

标签噪声在应用中严重降低了深度模型的泛化能力。有效的策略和方法,\textit{e.g.}重新加权或损失校正,旨在减轻训练神经网络时标签噪声的负面影响。这些现有的工作通常依赖于预先指定的架构和手动调整额外的超参数。在本文中,我们提出了翘曲概率推理(WarPI),以实现自适应纠正元学习场景中的分类网络的训练过程。与确定性模型相比,WarPI通过学习摊销元网络被制定为分层概率模型,可以解决样本模糊性,因此对严重的标签噪声更具鲁棒性。与现有的直接从损失中生成权重值的近似加权函数不同,我们的元网络被学习来从logits和标签的输入中估计纠正向量,这具有利用其中足够信息的能力。这为改进分类网络的学习过程提供了一种有效的方法,从而显著提高了网络的泛化能力。此外,将整流矢量建模为潜变量和学习元网络可以无缝集成到分类网络的SGD优化中。我们评估WarPI的四个基准的鲁棒学习与噪声标签,并实现新的国家的最先进的各种噪声类型。广泛的研究和分析也证明了我们的模型的有效性。

英文摘要:

Label noise significantly degrades the generalization ability of deep models in applications. Effective strategies and approaches, \textit{e.g.} re-weighting, or loss correction, are designed to alleviate the negative impact of label noise when training a neural network. Those existing works usually rely on the pre-specified architecture and manually tuning the additional hyper-parameters. In this paper, we propose warped probabilistic inference (WarPI) to achieve adaptively rectifying the training procedure for the classification network within the meta-learning scenario. In contrast to the deterministic models, WarPI is formulated as a hierarchical probabilistic model by learning an amortization meta-network, which can resolve sample ambiguity and be therefore more robust to serious label noise. Unlike the existing approximated weighting function of directly generating weight values from losses, our meta-network is learned to estimate a rectifying vector from the input of the logits and labels, which has the capability of leveraging sufficient information lying in them. This provides an effective way to rectify the learning procedure for the classification network, demonstrating a significant improvement of the generalization ability. Besides, modeling the rectifying vector as a latent variable and learning the meta-network can be seamlessly integrated into the SGD optimization of the classification network. We evaluate WarPI on four benchmarks of robust learning with noisy labels and achieve the new state-of-the-art under variant noise types. Extensive study and analysis also demonstrate the effectiveness of our model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑