Related papers: Enhanced Sample Selection with Confidence Tracking…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…

Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning…

Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. Annotator label uncertainty manifests in variations of labeling quality. Training with a single low-quality annotation per sample…

Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are…

Supervised deep learning depends on massive accurately annotated examples, which is usually impractical in many real-world scenarios. A typical alternative is learning from multiple noisy annotators. Numerous earlier works assume that all…

Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…

In many classification problems, misclassification costs are highly asymmetric, while training labels are often corrupted due to measurement error, annotator variability, or adversarial noise. The Neyman-Pearson multiclass classification…

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…

Real-world data is often ambiguous; for example, human annotation produces instances with multiple conflicting class labels. Partial-label learning (PLL) aims at training a classifier in this challenging setting, where each instance is…

In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels. The conventional PLL assumes the noisy labels are randomly generated (instance-independent),…

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each…

Deep learning has shown remarkable success in medical image analysis, but its reliance on large volumes of high-quality labeled data limits its applicability. While noisy labeled data are easier to obtain, directly incorporating them into…

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…

The "Curse of dimensionality" is prevalent across various data patterns, which increases the risk of model overfitting and leads to a decline in model classification performance. However, few studies have focused on this issue in Partial…

The negative impact of label noise is well studied in classical supervised learning yet remains an open research question in meta-learning. Meta-learners aim to adapt to unseen learning tasks by learning a good initial model in…

Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly…

Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled…

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…

Real-world datasets commonly exhibit noisy labels and class imbalance, such as long-tailed distributions. While previous research addresses this issue by differentiating noisy and clean samples, reliance on information from predictions…

Due to the lack of labels and the domain diversities, it is a challenge to study person re-identification in the cross-domain setting. An admirable method is to optimize the target model by assigning pseudo-labels for unlabeled samples…