arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.04337cs.LGcs.AIcs.CV
收藏

处理噪声标签的自迁移鲁棒学习

Robust Learning by Self-Transition for Handling Noisy Labels

NAVER AI Lab(NAVER人工智能实验室);Korea Advanced Institute of Science and Technology(韩国科学技术院)

Hwanjun Song, Minseok Kim, Dongmin Park, Yooju Shin, Jae-Gil Lee

摘要:

真实世界的数据不可避免地包含噪声标签,这导致深度神经网络的泛化能力差。众所周知,网络通常会在某个训练点之后开始快速记忆错误标记的样本。因此,为了应对标签噪声的挑战,我们提出了一种新的自过渡学习方法,称为MORPH,它会在从播种到进化的过渡点自动切换其学习阶段。在播种阶段,使用所有样本更新网络,以收集干净样本的种子。然后,在进化阶段,网络只使用可以说是干净的样本集进行更新,这正是通过更新后的网络不断扩展。因此,MORPH在整个训练期间有效地避免了对假标记样本的过拟合。使用五个真实世界或合成基准数据集进行的广泛实验表明,在鲁棒性和效率方面,与最先进的方法相比,该方法有了很大的改进。

英文摘要:

Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize false-labeled samples after a certain point of training. Thus, to counter the label noise challenge, we propose a novel self-transitional learning method called MORPH, which automatically switches its learning phase at the transition point from seeding to evolution. In the seeding phase, the network is updated using all the samples to collect a seed of clean samples. Then, in the evolution phase, the network is updated using only the set of arguably clean samples, which precisely keeps expanding by the updated network. Thus, MORPH effectively avoids the overfitting to false-labeled samples throughout the entire training period. Extensive experiments using five real-world or synthetic benchmark datasets demonstrate substantial improvements over state-of-the-art methods in terms of robustness and efficiency.

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。

↑