Related papers: Finding Label and Model Errors in Perception Data …
In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…
Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods…
Machine learning (ML) models are only as good as the data they are trained on. But recent studies have found datasets widely used to train and evaluate ML models, e.g. ImageNet, to have pervasive labeling errors. Erroneous labels on the…
Label noise poses a significant challenge in Earth Observation (EO), often degrading the performance and reliability of supervised Machine Learning (ML) models. Yet, given the critical nature of several EO applications, developing robust…
Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. We compare it to an alternative setting where each mini-batch…
Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…
Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples…
Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…
Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…
To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy…
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…
Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-critical systems such as automotive…
One of the major open challenges in self-driving cars is the ability to detect cars and pedestrians to safely navigate in the world. Deep learning-based object detector approaches have enabled great advances in using camera imagery to…
Machine learning (ML) is increasingly being used to support high-stakes decisions. However, there is frequently a construct gap: a gap between the construct of interest to the decision-making task and what is captured in proxies used as…
A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However,…
In learning tasks with label noise, improving model robustness against overfitting is a pivotal challenge because the model eventually memorizes labels, including the noisy ones. Identifying the samples with noisy labels and preventing the…
Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and predict the dynamics of such systems. A core issue with this approach…