Related papers: Co-matching: Combating Noisy Labels by Augmentatio…

Numerous researches have proved that deep neural networks (DNNs) can fit everything in the end even given data with noisy labels, and result in poor generalization performance. However, recent studies suggest that DNNs tend to gradually…

Deep learning requires data. A useful approach to obtain data is to be creative and mine data from various sources, that were created for different purposes. Unfortunately, this approach often leads to noisy labels. In this paper, we…

Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods. In this paper, we explore many kinds…

Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…

In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. However, training two networks with a set of noisy pseudo…

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…

Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual learning framework that simultaneously addresses both…

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations…

Label noise is pervasive in various real-world scenarios, posing challenges in supervised deep learning. Deep networks are vulnerable to such label-corrupted samples due to the memorization effect. One major stream of previous methods…

This paper develops novel conformal prediction methods for classification tasks that can automatically adapt to random label contamination in the calibration sample, leading to more informative prediction sets with stronger coverage…

Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in…

The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of…

Learning with curriculum has shown great effectiveness in tasks where the data contains noisy (corrupted) labels, since the curriculum can be used to re-weight or filter out noisy samples via proper design. However, obtaining curriculum…

Noisy labels collected with limited annotation cost prevent medical image segmentation algorithms from learning precise semantic correlations. Previous segmentation arts of learning with noisy labels merely perform a pixel-wise manner to…

Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk…

Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of the network to be similar in the vicinity of the observed…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…

Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks…