Related papers: Transfer Knowledge from Head to Tail: Uncertainty …

Instance-dependent label noise is realistic but rather challenging, where the label-corruption process depends on instances directly. It causes a severe distribution shift between the distributions of training and test data, which impairs…

In many real applications of statistical learning, collecting sufficiently many training data is often expensive, time-consuming, or even unrealistic. In this case, a transfer learning approach, which aims to leverage knowledge from a…

This paper studies the long-tailed semi-supervised learning (LTSSL) with distribution mismatch, where the class distribution of the labeled training data follows a long-tailed distribution and mismatches with that of the unlabeled training…

The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly determined by the average loss assessed on a testing set,…

We consider the estimation of small probabilities or other risk quantities associated with rare but catastrophic events. In the model-based literature, much of the focus has been devoted to efficient Monte Carlo computation or analytical…

Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task…

Many practical medical imaging scenarios include categories that are under-represented but still crucial. The relevance of image recognition models to real-world applications lies in their ability to generalize to these rare classes as well…

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is…

Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of distribution shifts…

Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL,…

Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these…

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the…

Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In this paper, we tackle…

Learning-based solutions for long-tailed recognition face difficulties in generalizing on balanced test datasets. Due to imbalanced data prior, the learned \textit{a posteriori} distribution is biased toward the most frequent (head)…

The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established,…

Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-limited media terminals. However, traditional KD methods…

Conformal Prediction (CP) is a popular method for uncertainty quantification that converts a pretrained model's point prediction into a prediction set, with the set size reflecting the model's confidence. Although existing CP methods are…

Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label…

Long-tailed datasets are very frequently encountered in real-world use cases where few classes or categories (known as majority or head classes) have higher number of data samples compared to the other classes (known as minority or tail…

Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder…