Related papers: Retraining with Predicted Hard Labels Provably Inc…

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

This paper presents a new approach to identifying and eliminating mislabeled training instances for supervised learning. The goal of this approach is to improve classification accuracies produced by learning algorithms by improving the…

In industry deep learning application, our manually labeled data has a certain number of noisy data. To solve this problem and achieve more than 90 score in dev dataset, we present a simple method to find the noisy data and re-label the…

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficult to obtain, which has motivated research on the training of…

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to…

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…

Because deep learning is vulnerable to noisy labels, sample selection techniques, which train networks with only clean labeled data, have attracted a great attention. However, if the labels are dominantly corrupted by few classes, these…

We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, yet its behavior and…

Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…