Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels

By Lu Jiang, Di Huang, Mason Liu, Weilong Yang. 2019

252 citations recorded by the source corpus.

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Sharpness-Aware Minimization for Efficiently Improving Generalization (2020, methodology): “However, simply bootstrapping SAM yields performance comparable to that of MentorMix (which is substantially more complex).”
Continual Learning on Noisy Data Streams via Self-Purified Replay (2021, background): “Learning with noisy labeled data has long been studied [92, 5, 54, 35].”
Regularizing Generative Adversarial Networks under Limited Data (2021, methodology): “Recent methods have shown successes in overcoming training data bias such as label noise [3, 16, 23, 24, 52, 40, 49, 66] and biased data distributions [56, 10, 35, 38, 9].”
MoPro: Webly Supervised Learning with Momentum Prototypes (2020, methodology): “…which commonly occur in real-world web datasets; (2) most methods are computational-heavy due to co-training (Han et al., 2018; Li et al., 2020a; Jiang et al., 2018; 2020), iterative training (Tanaka et al., 2018; Yi & Wu, 2019; Wang et al., 2018; Chen et al., 2019), or meta-learning (Li et…”
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise (2020, unknown): “y. The airp. is airplane for short. IDN easily, the generalization performance degenerates at early stages of training. The observation is consistent with the ﬁndings on real-world noise presented by Jiang et al. (2020). The memorization effect is less signiﬁcant. The memorization effect (Arpit et a”
Confident Learning: Estimating Uncertainty in Dataset Labels (2019, background): “, 2020), and the realistic noisy label benchmark CNWL (Jiang et al., 2020); evaluation of CL methods using other non-neural network models, such as random forests and XGBoost; examination of other threshold function formulations; examination of label errors in test sets and they affect machine learn”
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks (2021, methodology): “As shown in Foret et al. (2021), SAM is as robust to label noise in the training data as MentorMix (Jiang et al., 2020), which is a state-of-the-art method.”
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations (2021, background): “• Interventions: human interventions in data generation [Jiang et al., 2020] and non-representative data collection process [Song et al., 2019] might disturb the original noisy-label pattern.”