Probabilistic End-To-End Noise Correction for Learning With Noisy Labels

By Kun Yi, Jianxin Wu. 2019

488 citations recorded by the source corpus.

Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and accuracies drop dramatically. To address this problem, we propose an end-to-end framework called PENCIL, which can update both network parameters and label estimations as label distributions. PENCIL is independent of the backbone network structure and does not need an auxiliary clean dataset or prior information about noise, thus it is more general and robust than existing methods and is easy to apply. PENCIL outperformed previous state-of-the-art methods by large margins on both synthetic and real-world datasets with different noise types and noise rates. Experiments show that PENCIL is robust on clean datasets, too.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization (2020, background): “In addition to the aforementioned approaches, there are some other deep learning solutions [13, 17] to deal with noisy labels, including pseudo-label based [35, 40] and robust loss based approaches [28, 46].”
Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey (2019, methodology): “A similar approach is used in [59]”
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning (2021, methodology): “Inspired by noise correction work (Yi & Wu, 2019), Wang & Wu (2020) attempt to update the pseudo-labels through an optimization framework.”
DualGraph: A graph-based method for reasoning about label noise (2021, methodology): “These datasets are popularly used for the evaluation of learning with noisy labels in previous literatures [7, 11, 29, 36, 35].”
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision (2023, methodology): “1 We call the performance of the weak supervisor the weak performance , and we generate weak labels by taking the weak model’s predictions on a held-out set of examples.”
DivideMix: Learning with Noisy Labels as Semi-supervised Learning (2020, methodology): “…2019) proposes a gradient based method to ﬁnd model parameters that are more noise-tolerant; Joint-Optim (Tanaka et al., 2018) and P-correction (Yi & Wu, 2019) jointly optimize the sample labels and the network parameters; M-correction (Arazo et al., 2019) models sample loss with BMM and…”
Delving Deep Into Label Smoothing (2020, unknown): “PENCIL [54] proposed a novel framework to learn the correct label and model’s weights at the same time.”
Early-Learning Regularization Prevents Memorization of Noisy Labels (2020, background): “This can be achieved by computing new labels equal to the probabilities estimated by the model (known as soft labels ) or to one-hot vectors representing the model predictions ( hard labels ) [38, 49].”
An Overview of Deep Semi-Supervised Learning (2020, methodology): “One type of correction consists of treating all the examples as equal and relabeling the noisy examples, where proxy labels methods can be used for the relabeling procedure [174, 101, 127].”
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics (2022, methodology): “Prior work has developed a rough taxonomy of data properties, or metadata which different examples might exhibit, including but not limited to: noisy [68, 71, 62, 63], atypical [25, 10, 21, 60], challenging [24, 3, 8, 49, 2], prototypical or core subset selection [49, 55, 56, 27] and out-of-distribu”