Related papers: Posterior Re-calibration for Imbalanced Datasets

We study the effect of one type of imbalance often present in real-life multilingual classification datasets: an uneven distribution of labels across languages. We show evidence that fine-tuning a transformer-based Large Language Model…

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the…

In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…

Due to the inherent imbalance in real-world datasets, na\"ive Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

We propose a new framework for binary classification in transfer learning settings where both covariate and label distributions may shift between source and target domains. Unlike traditional covariate shift or label shift assumptions, we…

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to…

Semi-supervised Learning (SSL) reduces the need for extensive annotations in deep learning, but the more realistic challenge of imbalanced data distribution in SSL remains largely unexplored. In Class Imbalanced Semi-supervised Learning…

Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored…

Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for downstream data becomes crucial in Bayesian model averaging…

Deploying deep models in real-world scenarios entails a number of challenges, including computational efficiency and real-world (e.g., long-tailed) data distributions. We address the combined challenge of learning long-tailed distributions…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic…

Most classification models work by first predicting a posterior probability distribution over all classes and then selecting that class with the largest estimated probability. In many settings however, the quality of posterior probability…

Adversarial approach has been widely used for data generation in the last few years. However, this approach has not been extensively utilized for classifier training. In this paper, we propose an adversarial framework for classifier…

To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on searching the latent…

Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model…

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods…

Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed dataset to uniform…

Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. The task is to learn a…