MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels

By Lu Jiang, Zhengyuan Zhou, Thomas K. Leung, Li-Jia Li, Li Fei-Fei. 2017

83 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Optimization & Training

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Optimization & Training

Citations in the corpus

Learning to Reweight Examples for Robust Deep Learning (2018, methodology): “More recently, Jiang et al. (2017) proposed to use a meta-learning LSTM to output the weights of the examples based on the training loss.”
Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018, methodology): “Comparison of error flow among MentorNet (M-Net) [7], Decoupling [8] and Co-teaching.”
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels (2018, methodology): “[15] used a LSTM network on top of a classification model to learn the optimal weights on each sample, while Ren, et al.”
Facial Expression Recognition with Inconsistently Annotated Datasets (2018, methodology): “Net[13], augmenting the prediction objective with the similarities and improving the learner iteratively using bootstrapping[15], and other approaches that introducing constrains.”
Dimensionality-Driven Learning with Noisy Labels (2018, background): “An alternative is to correct noisy labels to their true labels via a clean label inference step (Vahdat, 2017; Veit et al., 2017; Jiang et al., 2017; Li et al., 2017).”
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? (2018, background): “…(Recht et al., 2011; Yun et al., 2014; Petroni & Querzoni, 2014), to training deep neural networks (Dean et al., 2012a; Zhang et al., 2013; Paine et al., 2013; Zhang et al., 2015; Grover et al., 2015; Jiang et al., 2017) and representation learning (Grover & Leskovec, 2016; Grover et al., 2018a;b).”
NLNL: Negative Learning for Noisy Labels (2019, methodology): “In other studies, each training sample is re-weighted differently depending on the reliability of the given label [13, 27, 20].”
Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications (2019, background): “Similarly, (Jiang et al., 2017) have an auxiliary model predict the curriculum.”
Robust Inference via Generative Classifiers for Handling Noisy Labels (2019, methodology): “We also consider the following methods that require to train multiple networks, i.e., an ensemble of classiﬁers or a meta-learning model: Decoupling (Malach & Shalev-Shwartz, 2017), MentorNet (Jiang et al., 2018) and Co-teaching (Han et al., 2018b).”
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images (2018, methodology): “Convolutional neural networks have recently been applied to training a robust model with noisy data [39,30,25,17,15].”
L_DMI: An Information-theoretic Noise-robust Loss Function (2019, unknown): “For example, teacher-student curriculum learning framework [14] and co-teaching framework [10] have been shown to be helpful.”