Related papers: Optimized Gradient Clipping for Noisy Label Learni…
Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the…
OOD-CV challenge is an out-of-distribution generalization task. In this challenge, our core solution can be summarized as that Noisy Label Learning Is A Strong Test-Time Domain Adaptation Optimizer. Briefly speaking, our main pipeline can…
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…
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…
Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…
We introduce a novel approach for batch selection in Stochastic Gradient Descent (SGD) training, leveraging combinatorial bandit algorithms. Our methodology focuses on optimizing the learning process in the presence of label noise, a…
Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…
Graph neural networks (GNNs) have achieved state-of-the-art performance for node classification on graphs. The vast majority of existing works assume that genuine node labels are always provided for training. However, there has been very…
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previous works often rely on massive hand-crafted losses and…
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…
We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…
Neural networks trained with stochastic gradient descent exhibit an inductive bias towards simpler decision boundaries, typically converging to a narrow family of functions, and often fail to capture more complex features. This phenomenon…
In this paper, we present a simple yet effective provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning. Our method is a simple modification to momentum SGD where we assign an individual…
The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This effect is amplified in difficult tasks such as object detection. Dealing with errors in datasets is often…
Due to the existence of label noise in web images and the high memorization capacity of deep neural networks, training deep fine-grained (FG) models directly through web images tends to have an inferior recognition ability. In the…
Label noise in training data can significantly degrade a model's generalization performance for supervised learning tasks. Here we focus on the problem that noisy labels are primarily mislabeled samples, which tend to be concentrated near…
Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…
Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an…
Label distribution learning can characterize the polysemy of an instance through label distributions. However, some noise and uncertainty may be introduced into the label space when processing label distribution data due to artificial or…
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,…