Related papers: Learning with Instance-Dependent Label Noise: A Sa…
Label noise in real-world datasets encodes wrong correlation patterns and impairs the generalization of deep neural networks (DNNs). It is critical to find efficient ways to detect corrupted patterns. Current methods primarily focus on…
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;…
Noisy labels are both inevitable and problematic in machine learning methods, as they negatively impact models' generalization ability by causing overfitting. In the context of learning with noise, the transition matrix plays a crucial role…
In deep learning (DL) systems, label noise in training datasets often degrades model performance, as models may learn incorrect patterns from mislabeled data. The area of Learning with Noisy Labels (LNL) has introduced methods to…
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…
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…
We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to…
Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…
Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…
Because deep learning is vulnerable to noisy labels, sample selection techniques, which train networks with only clean labeled data, have attracted a great attention. However, if the labels are dominantly corrupted by few classes, these…
The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding "anchor…
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…
In recent years, deep neural networks (DNNs) have gained remarkable achievement in computer vision tasks, and the success of DNNs often depends greatly on the richness of data. However, the acquisition process of data and high-quality…
Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via…
This paper aims to provide understandings for the effect of an over-parameterized model, e.g. a deep neural network, memorizing instance-dependent noisy labels. We first quantify the harms caused by memorizing noisy instances, and show the…
Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection…
Existing research on learning with noisy labels predominantly focuses on synthetic label noise. Although synthetic noise possesses well-defined structural properties, it often fails to accurately replicate real-world noise patterns. In…
Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two…
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…
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…