Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

By Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, Deyu Meng. 2019

1,031 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.

Citations in the corpus

Long-Tailed Class Incremental Learning (2022, methodology): “Learning from long-tailed distributions has been approach by re-sampling [11,15] or re-weighting [21,36,48] head classes and tail classes to learn a balanced classifier.”
Learngene: From Open-World to Your Learning Task (2021, methodology): “Meta-learning: There is a three-way taxonomy across optimization-based methods (Finn, Abbeel, and Levine 2017; Shu et al. 2019), model-based methods (Ravi and Larochelle 2017; Santoro et al.”
Meta-Learning in Neural Networks: A Survey (2020, background): “weighs to down-weight noisy samples [147], or learning an initial condition robust to noisy label training [94].”
Equalization Loss for Long-Tailed Object Recognition (2020, background): “†means that the results are copied from origin paper [5, 40].”
Robust Learning by Self-Transition for Handling Noisy Labels (2020, background): “Other Directions: Beyond the supervised learning scope, MetaWeight-Net [32] employs a meta-learning approach to reweight the loss of the training samples.”
Synthetic vs Real: Deep Learning on Controlled Noise (2019, background): “Following (Jiang et al., 2018; Shu et al., 2019; Arazo et al., 2019), the noisy CIFAR-100 data are of uniform label-ﬂipping noise, where the label of each image is independently changed to a uniform (incorrect) class with probability p , where p is the noise level and is set to 20%, 40%, 60%, and…”
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective (2020, background): “[7] Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng.”
Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax (2020, methodology): “One may consider using solutions to long-tail classiﬁcation to overcome such an issue, including re-sampling training instances to balance the distribution [16, 8, 34, 27] and re-weighting classiﬁcation loss at category level [6, 2, 19] or instance level [24, 35].”
Learning to Reweight with Deep Interactions (2021, methodology): “Discussions: Compared to previous work (Jiang et al. 2018; Shu et al. 2019; Fan et al. 2018; Wu et al. 2018), except for the key differences that we use internal states as features, there are some differences in optimization.”
MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation (2021, unknown): “where w(T ) represents the optimal segmentation net with the minimal corrected loss on the noisy pseudo-labeled target data, and the updated T ∗ should minimize the empirical loss on meta data with the optimal segmentation net [36, 37, 43].”
RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning (2021, background): “[45] Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng.”
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning (2022, methodology): “We use an online optimization strategy (Shu et al., 2019) instead of nested optimization loops to optimize ω ∗ and θ ∗ p for training efficiency.”
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (2020, unknown): “The instance-level re-weighting [28, 29, 30] is also a practical solution.”
Confident Learning: Estimating Uncertainty in Dataset Labels (2019, background): “, 2015; Goldberger and Ben-Reuven, 2017), example weighting (Jiang et al., 2018; Shu et al., 2019), coteaching (Han et al.”
Delving Deep Into Label Smoothing (2020, unknown): “To reduce such damage to the generalization ability of DNNs, researchers have proposed many methods, including weighting the samples [46], [47] and inferring the real labels of the noisy samples [11], [51].”