On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “WebVision”

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularizationcs.LG

Adaptive regularization tackles heteroskedastic and imbalanced datasets in deep learning.

problem Heteroskedastic and imbalanced datasets challenge deep learning due to varying label uncertainty and long-tailed label distributions.

method Data-dependent adaptive regularization that applies stronger regularization to higher-uncertainty, lower-density regions.

result Significant improvement in noise-robust deep learning over other methods on benchmark tasks.

deep learning heteroskedastic imbalance adaptive regularization WebVision

2020-06-29abs ↗pdf ↗

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscs.LG

Proposes a new loss function for learning with noisy labels.

problem Improving model learnability with noisy labels.

method Uses generalized Jensen-Shannon divergence as a noise-robust loss function.

result Shows state-of-the-art results on noisy data.

Jensen-Shannon divergence noise robustness loss function categorical loss mean absolute error

2021-05-10abs ↗pdf ↗

Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labelscs.LG

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This pa…

2019-11-21abs ↗pdf ↗

Coresets for Robust Training of Neural Networks against Noisy Labelscs.LG

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

problem Overfitting of neural networks trained with noisy labels.

method Selects weighted subsets (coresets) of clean data points to approximate low-rank Jacobian matrix.

result Gradient descent applied to coreset subsets does not overfit noisy labels.

neural networks noisy labels robust training coresets gradient descent

2020-11-15abs ↗pdf ↗

Consistency Regularization Can Improve Robustness to Label Noisecs.LG

Consistency regularization improves robustness to noisy labels.

problem Improving model robustness to noisy labels in machine learning.

method Empirical study of consistency regularization on noisy datasets.

result Consistency regularization improves model robustness to label noise.

consistency regularization robustness label noise machine learning semi-supervised learning

2021-10-04abs ↗pdf ↗

Improved image classification accuracy with a probabilistic model of label noise.

problem Noisy labels in large-scale image classification datasets.

method A probabilistic model using a multivariate Normal distribution on the final hidden layer of a neural network, capturing input-dependent label noise.

result Significantly improved accuracy on various datasets compared to standard methods.

image classification label noise aleatoric uncertainty heteroscedastic noise deep learning

2021-05-19abs ↗pdf ↗