mlsanityData to 7 Oct 2026

Learning Deep Networks from Noisy Labels with Dropout Regularization

arXiv 1705.03419 ↗First posted 9 May 2017cs.CV cs.LG stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment a standard deep network with a softmax layer that models the label noise statistics. Then, we train the deep network and noise model jointly via end-to-end stochastic gradient descent on the (perhaps mislabeled) dataset. The augmented model is overdetermined, so in order to encourage the learning of a non-trivial noise model, we apply dropout regularization to the weights of the noise model during training. Numerical experiments on noisy versions of the CIFAR-10 and MNIST datasets show that the proposed dropout technique outperforms state-of-the-art methods.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 6; 2023: 3; 2024: 9; 2025: 2.

32 papers.

Sort:

By area:

  1. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  2. 2021Sample Selection for Fair and Robust Trainingcited by 48
  3. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 42
  4. 2022Characterizing Datapoints via Second-Split Forgettingcited by 37
  5. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  6. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  7. 2021Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyondcited by 16
  8. 2023Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learningcited by 11
  9. 2024SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustnesscited by 10
  10. 2021Noisy Annotation Refinement for Object Detectioncited by 9
  11. 2024Learning Discriminative Dynamics with Label Corruption for Noisy Label Detectioncited by 8
  12. 2022Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillationcited by 7
20 more
  1. 2024RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Taskscited by 6
  2. 2025Policy Learning from Large Vision-Language Model Feedback without Reward Modelingcited by 4
  3. 2021On the Evaluation of Sequential Machine Learning for Network Intrusion Detectioncited by 3
  4. 2022Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimationcited by 3
  5. 2022Robust Product Classification with Instance-Dependent Noisecited by 3
  6. 2024Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processescited by 3
  7. 2021Training Classifiers that are Universally Robust to All Label Noise Levelscited by 2
  8. 2023Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspectivecited by 2
  9. 2024AlleNoise: large-scale text classification benchmark dataset with real-world label noisecited by 2
  10. 2024Granular-ball Representation Learning for Deep CNN on Learning with Label Noisecited by 2
  11. 2021A Novel Perspective for Positive-Unlabeled Learning via Noisy Labelscited by 1
  12. 2023FS-Net: Full Scale Network and Adaptive Threshold for Improving Extraction of Micro-Retinal Vessel Structurescited by 1
  13. 2024Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labelscited by 1
  14. 2024NoisyAG-News: A Benchmark for Addressing Instance-Dependent Noise in Text Classificationcited by 1
  15. 2024Training Gradient Boosted Decision Trees on Tabular Data Containing Label Noise for Classification Taskscited by 1
  16. 2021Hypothesis Testing for Class-Conditional Label Noisecited by 0
  17. 2021A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during trainingcited by 0
  18. 2022"Is not the truth the truth?": Analyzing the Impact of User Validations for Bus In/Out Detection in Smartphone-based Surveyscited by 0
  19. 2022Deep Learning with Label Noise: A Hierarchical Approachcited by 0
  20. 2025MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality imagescited by 0