Related papers: Learning with Confidence: Training Better Classifi…

The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…

Recently, learning with soft labels has been shown to achieve better performance than learning with hard labels in terms of model generalization, calibration, and robustness. However, collecting pointwise labeling confidence for all…

Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning…

Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision. It has been shown that complex noise-handling techniques - by modeling, cleaning or filtering the…

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…

We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic model and equations that characterize the problem. This includes…

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning…

Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…

Recent studies on the memorization effects of deep neural networks on noisy labels show that the networks first fit the correctly-labeled training samples before memorizing the mislabeled samples. Motivated by this early-learning…

Soft labels generated by teacher models have become a dominant paradigm for knowledge transfer and recent large-scale dataset distillation such as SRe2L, RDED, LPLD, offering richer supervision than conventional hard labels. However, we…

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…

Extracting noisy or incorrectly labeled samples from a labeled dataset with hard/difficult samples is an important yet under-explored topic. Two general and often independent lines of work exist, one focuses on addressing noisy labels, and…

Generating confidence calibrated outputs is of utmost importance for the applications of deep neural networks in safety-critical decision-making systems. The output of a neural network is a probability distribution where the scores are…

Knowledge distillation has been widely adopted in a variety of tasks and has achieved remarkable successes. Since its inception, many researchers have been intrigued by the dark knowledge hidden in the outputs of the teacher model.…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its…

Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more information than sparse annotations (like hard labels), they are…

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…