论文标题
通过自我运输来处理嘈杂标签的强大学习
Robust Learning by Self-Transition for Handling Noisy Labels
论文作者
论文摘要
现实世界中的数据不可避免地包含嘈杂的标签，这会引起深神经网络的不良概括。众所周知，在一定的训练点之后，网络通常开始迅速记住假标记的样本。因此，为了应对标签噪声挑战，我们提出了一种称为Morph的新型自我经际学习方法，该方法会自动切换其从播种到进化的过渡点的学习阶段。在播种阶段，使用所有样品更新网络以收集干净样品的种子。然后，在进化阶段，仅使用一组可以说清洁的样本来更新网络，该样本可以通过更新的网络不断扩展。因此，在整个训练期间，Morph有效地避免了对假标记的样本的过度拟合。使用五个现实世界或合成基准数据集进行的广泛实验表明，就鲁棒性和效率而言，对最先进的方法进行了实质性改进。
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.
