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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

15 results for “Clothing1M”

Joint Optimization Framework for Learning with Noisy Labelscs.CV

Framework corrects noisy labels to improve DNN performance.

problem Performance degradation due to noisy labels in large-scale datasets.

method Joint optimization of DNN parameters and true labels estimation.

result Significantly outperforms state-of-the-art methods in experiments.

Deep learning Noisy labels CIFAR-10 Clothing1M Performance improvement

2018-03-30abs ↗pdf ↗

Meta Soft Label Generation for Noisy Labelscs.CV

MSLG generates soft labels to improve DNN performance on noisy datasets.

problem Significant performance degradation of DNNs due to noisy labels.

method Meta-learning techniques to estimate optimal label distribution and iteratively update soft labels.

result MSLG outperforms state-of-the-art methods by a large margin on various datasets.

Meta Learning Soft Labels Deep Neural Networks Noisy Labels CIFAR10

2020-07-11abs ↗pdf ↗

TrustNet: Learning from Trusted Data Against (A)symmetric Label Noisecs.LG

TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.

problem Robustness to label noise in weakly-supervised learning.

method TrustNet learns noise patterns from trusted data, then trains a robust classifier using these patterns.

result TrustNet outperforms state-of-the-art methods in robustness to various noise patterns.

label noise weakly supervised learning robustness trustworthy data CIFAR-10

2020-07-13abs ↗pdf ↗

Learning to Learn from Noisy Labeled Datacs.LG

A method to train deep neural networks on noisy labeled data.

problem Training deep neural networks on noisy labeled data causes performance degradation.

method A noise-tolerant training algorithm that simulates actual training with synthetic noisy labels.

result The proposed method outperforms state-of-the-art baselines on noisy CIFAR-10 and Clothing1M datasets.

deep learning noisy labels meta-learning gradient update synthetic data

2018-12-13abs ↗pdf ↗

Combating noisy labels by agreement: A joint training method with co-regularizationcs.CV

JoCoR improves deep learning with noisy labels by reducing network diversity.

problem Learning with noisy labels in deep learning.

method JoCoR uses two networks to make predictions, calculates a joint loss with Co-Regularization, and updates both networks simultaneously.

result JoCoR outperforms state-of-the-art approaches in learning with noisy labels.

noisy labels deep learning weakly supervised learning Co-Regularization joint training

2020-03-05abs ↗pdf ↗

SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixingcs.LG

SelectMix improves deep learning robustness against noisy labels.

problem Deep neural networks memorize noisy labels, degrading performance.

method Confidence-guided targeted sample mixing with soft labels.

result SelectMix consistently outperforms baseline methods on noisy label datasets.

deep learning label noise robustness mixup confidence analysis

2025-09-14abs ↗pdf ↗

Improving Generalization by Controlling Label-Noise Information in Neural Network Weightscs.LG

New method reduces neural network memorization of noisy labels.

problem Neural networks memorize label noise, leading to poor generalization.

method Proposes an auxiliary network that predicts gradients without labels.

result Reduces memorization of label-noise, improving generalization.

neural networks label-noise memorization generalization gradient prediction

2020-02-19abs ↗pdf ↗

SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustnesscs.LG

SAP corrects model for label noise by identifying and removing noisy samples.

problem Label corruption degrades model performance; acquiring perfect labels is costly.

method SAP uses SVD to identify and project model weights onto a clean activation space.

result SAP improves model generalization by up to 6% on CIFAR dataset with 25% synthetic corruption.

label noise machine unlearning SVD activation projection model correction

2024-03-13abs ↗pdf ↗

Masking: A New Perspective of Noisy Supervisioncs.LG

Paper proposes Masking for robust classifier learning from noisy labels.

problem Learning robust classifiers from noisy labels with unknown noise transition matrix.

method Human-assisted approach called Masking that conveys invalid class transitions and speculates noise transition matrix structure.

result Masking significantly improves robustness of classifiers compared to existing methods.

classifier learning noisy labels noise transition matrix human-assisted robustness

2018-05-21abs ↗pdf ↗

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscs.LG

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

problem Learning with noisy labels is challenging due to inaccurate labels.

method Estimates transition matrix using clusterability condition and noisy labels.

result Estimation of transition matrix is more accurate and efficient than anchor points.

label noise noisy labels clusterability anchor points transition matrix

2021-02-10abs ↗pdf ↗

ExpertNet: Adversarial Learning and Recovery Against Noisy Labelscs.LG

ExpertNet uses noisy labels to improve deep learning robustness.

problem Improving deep learning robustness against noisy labels.

method ExpertNet framework combining Amateur and Expert models, iteratively learning from noisy labels and images.

result ExpertNet achieves robust classification with as little as 20-50% training data, outperforming state-of-the-art models.

deep learning noisy labels adversarial learning image classification robustness

2020-07-10abs ↗pdf ↗

L_DMI: An Information-theoretic Noise-robust Loss Functioncs.LG

Proposes a new loss function for robust training of deep neural networks against noisy labels.

problem Training deep neural networks with noisy labels, especially instance-independent noise.

method Introduces a novel information-theoretic loss function, L_DMI, based on Determinant based Mutual Information (DMI).

result L_DMI is the first provably robust loss function to instance-independent label noise, without requiring auxiliary information.

Deep Learning Noise Robustness Information Theory Mutual Information Label Noise

2019-09-08abs ↗pdf ↗

Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcs.LG

CORES2 removes noisy labels by sieving out corrupted examples.

problem Instance-dependent label noise degrades DNN performance.

method CORES2 (COnfidence REgularized Sample Sieve) progressively sieves out corrupted examples.

result CORES2 provides theoretical guarantees for filtering out corrupted examples.

label noise deep learning sample sieving instance-dependent CIFAR10

2020-10-05abs ↗pdf ↗

Compressing Features for Learning with Noisy Labelscs.LG

Paper tackles noisy labels by compressing feature representations.

problem Learning with noisy labels leads to overfitting and poor generalization.

method Introduces compression inductive bias using Dropout and Nested Dropout.

result Compression helps in combating label noise and improving performance.

Noisy Labels Feature Compression Dropout Nested Dropout Co-teaching

2022-06-27abs ↗pdf ↗

Safeguarded Dynamic Label Regression for Generalized Noisy Supervisioncs.LG

Proposes a new method to handle noisy labels without needing accurate noise transition estimation.

problem Learning with noisy labels in the presence of class-conditional noise.

method Introduces a Latent Class-Conditional Noise (LCCN) model that embeds noise transition in a Bayesian framework and iteratively infers latent labels.

result Demonstrates superior performance compared to state-of-the-art methods on various noisy label datasets.

noisy labels Bayesian framework dynamic label regression class-conditional noise open-set noise

2019-03-06abs ↗pdf ↗