Related papers: Robust Long-Tailed Learning under Label Noise
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…
Label noise is a significant obstacle in deep learning model training. It can have a considerable impact on the performance of image classification models, particularly deep neural networks, which are especially susceptible because they…
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning…
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels. In this paper, we find that the test accuracy…
Partial-label learning (PLL) is an important branch of weakly supervised learning where the single ground truth resides in a set of candidate labels, while the research rarely considers the label imbalance. A recent study for imbalanced…
High-dimensional linear regression is a fundamental tool in modern statistics, particularly when the number of predictors exceeds the sample size. The classical Lasso, which relies on the squared loss, performs well under Gaussian noise…
Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…
Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has…
A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated and human-gathered dataset. Although…
Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in the testing stage.…
In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning, which arise from dependencies on instances and labels.…
We investigate high-dimensional sparse regression when both the noise and the design matrix exhibit heavy-tailed behavior. Standard algorithms typically fail in this regime, as heavy-tailed covariates distort the empirical risk geometry. We…
Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…
Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic, but assume a single…
Conventional federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Worse still, the F-LN problem is exacerbated by the…
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…
In real medical data, training samples typically show long-tailed distributions with multiple labels. Class distribution of the medical data has a long-tailed shape, in which the incidence of different diseases is quite varied, and at the…
Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical…
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…