论文标题
CNLL：连续嘈杂标签学习的半监督方法
CNLL: A Semi-supervised Approach For Continual Noisy Label Learning
论文作者
论文摘要
持续学习的任务需要仔细设计可以解决灾难性遗忘的算法。但是，在现实情况下，嘈杂的标签似乎不可避免地加剧了这种情况。尽管很少有研究解决了在嘈杂标签下持续学习的问题，但在大多数情况下，较长的培训时间和复杂的培训方案限制了其应用。相比之下，我们提出了一种简单的纯化技术，以有效地清洁既具有成本效益又更准确的在线数据流。纯化后，我们以半监督的方式进行微调，以确保所有可用样品的参与。以这种方式培训有助于我们学习更好的代表，从而导致最先进的表现。通过在3个基准数据集（MNIST，CIFAR10和CIFAR100）上进行广泛的实验，我们显示了我们提出的方法的有效性。我们的CIFAR10的性能增长为24.8％，与以前的SOTA方法相比，噪声为20％。我们的代码公开可用。
The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies have addressed the issue of continual learning under noisy labels, long training time and complicated training schemes limit their applications in most cases. In contrast, we propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. Training in this fashion helps us learn a better representation that results in state-of-the-art (SOTA) performance. Through extensive experimentation on 3 benchmark datasets, MNIST, CIFAR10 and CIFAR100, we show the effectiveness of our proposed approach. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods. Our code is publicly available.
