arXiv research

Optimizes noisy IS with better proposal densities.

Class2Simi reduces noise in noisy label learning by transforming noisy class labels into noisy similarity labels.

Quantum neural networks can approximate noisy functions accurately.

Paper improves $\ell^{0}$-SSC for noisy data by proving SDP and proposing Noisy-DR-$\ell^{0}$-SSC.

Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance of DNNs. We propose a novel technique to identify data with noisy lab…

ExpertNet uses noisy labels to improve deep learning robustness.

Paper tackles noisy similarity labels for multi-class classification.

Proposes coreset method for robust training of neural networks with noisy labels.

MARVEL curbs memorization of noisy labels in deep nets.

Paper explains why small-loss criterion works for learning from noisy labels.

Study how noisy labels affect semi-supervised learning.

CrossFilter tackles noisy labels in audio tagging.

CNT leverages noisy targets to guide model learning.

Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive poste…

CbMLC improves multi-label classification with noisy labels.

A new method simplifies noisy data filtering for CNNs.

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to train…

Paper shows how noisy data can improve robust decision-making.

Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance. To mitigate this issue, we provide a simple but effective baseline method that is robust to noisy labels, even with severe noise. Our objective involves a variance regulariz…

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance de…

The paper tackles learning true rankings from noisy, incomplete data.

Estimates linear model from noisy covariates and instruments using spectral regularization.

A corrected EI acquisition function handles noisy observations in Bayesian optimization.

Paper proposes an alternative to anchor points for learning with noisy labels.

Bayes classifier cannot be learned from noisy labels without knowing noise distribution.

Simple k-NN filtering improves model accuracy on noisy labels.

Paper tackles noisy labels for non-decomposable performance measures.

This work explores how neural network architecture affects robustness to noisy labels.

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed …

Study efficient graph optimization with noisy data.

We present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base cl…

The paper analyzes generalization of noisy iterative algorithms using communication theory.

Deep neural networks have been proved efficient for medical image denoising. Current training methods require both noisy and clean images. However, clean images cannot be acquired for many practical medical applications due to naturally noisy signal, such as dynamic imaging, spectral computed tomography, arterial spin …

Survey on deep learning robust training methods for noisy labels.

DynaCor detects noisy labels by learning from corrupted training signals.

Study real-world noisy labels from human annotations for better understanding.

New methods ensure fairness in noisy protected groups.

We investigate the problem of estimating a given real symmetric signal matrix $\textbf{C}$ from a noisy observation matrix $\textbf{M}$ in the limit of large dimension. We consider the case where the noisy measurement $\textbf{M}$ comes either from an arbitrary additive or multiplicative rotational invariant perturbati…

Diffusion models tackle noisy inverse problems with posterior sampling.

The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.

We consider the problem of clustering noisy high-dimensional data points into a union of low-dimensional subspaces and a set of outliers. The number of subspaces, their dimensions, and their orientations are unknown. A probabilistic performance analysis of the thresholding-based subspace clustering (TSC) algorithm intr…

Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.

Proposes PA-DSL for correcting noisy human labels in automated data labeling.

Generates positive examples from noisy data streams.

Paper tackles noisy bandit feedback for multiclass classification.

New metric compares noisy neural trajectories using optimal transport.

A fast method approximates likelihood scores for noisy linear inverse problems.

VBMC+VIQR outperforms noisy models in Bayesian inference.