ReMix: Calibrated Resampling for Class Imbalance in Deep learning
- URL: http://arxiv.org/abs/2012.02312v1
- Date: Thu, 3 Dec 2020 22:39:26 GMT
- Title: ReMix: Calibrated Resampling for Class Imbalance in Deep learning
- Authors: Colin Bellinger, Roberto Corizzo, Nathalie Japkowicz
- Abstract summary: We propose ReMix, a training technique that leverages batch resampling, instance mixing and soft-labels to enable the induction of robust deep models for imbalanced learning.
Our results show that dense nets and CNNs trained with ReMix generally outperform the alternatives according to the g-mean and are better calibrated according to the balanced Brier score.
- Score: 7.470456340416917
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Class imbalance is a problem of significant importance in applied deep
learning where trained models are exploited for decision support and automated
decisions in critical areas such as health and medicine, transportation, and
finance. The challenge of learning deep models from imbalanced training data
remains high, and the state-of-the-art solutions are typically data dependent
and primarily focused on image data. Real-world imbalanced classification
problems, however, are much more diverse thus necessitating a general solution
that can be applied to tabular, image and text data. In this paper, we propose
ReMix, a training technique that leverages batch resampling, instance mixing
and soft-labels to enable the induction of robust deep models for imbalanced
learning. Our results show that dense nets and CNNs trained with ReMix
generally outperform the alternatives according to the g-mean and are better
calibrated according to the balanced Brier score.
Related papers
- Gradient Reweighting: Towards Imbalanced Class-Incremental Learning [8.438092346233054]
Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data.
A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution.
We show that this dual imbalance issue causes skewed gradient updates with biased weights in FC layers, thus inducing over/under-fitting and catastrophic forgetting in CIL.
arXiv Detail & Related papers (2024-02-28T18:08:03Z) - Simplifying Neural Network Training Under Class Imbalance [77.39968702907817]
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models.
The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures.
We demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods.
arXiv Detail & Related papers (2023-12-05T05:52:44Z) - SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised
Learning [101.86916775218403]
This paper revisits the popular pseudo-labeling methods via a unified sample weighting formulation.
We propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training.
In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.
arXiv Detail & Related papers (2023-01-26T03:53:25Z) - Learning Sample Reweighting for Accuracy and Adversarial Robustness [15.591611864928659]
We propose a novel adversarial training framework that learns to reweight the loss associated with individual training samples based on a notion of class-conditioned margin.
Our approach consistently improves both clean and robust accuracy compared to related methods and state-of-the-art baselines.
arXiv Detail & Related papers (2022-10-20T18:25:11Z) - Density-Aware Personalized Training for Risk Prediction in Imbalanced
Medical Data [89.79617468457393]
Training models with imbalance rate (class density discrepancy) may lead to suboptimal prediction.
We propose a framework for training models for this imbalance issue.
We demonstrate our model's improved performance in real-world medical datasets.
arXiv Detail & Related papers (2022-07-23T00:39:53Z) - Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for
Imbalanced Classification [11.673344551762822]
Deep neural networks generally perform poorly with datasets that suffer from quantity imbalance and classification difficulty imbalance between different classes.
A phased progressive learning schedule was proposed for smoothly transferring the training emphasis from representation learning to upper classifier training.
Our code will be open source soon.
arXiv Detail & Related papers (2022-05-24T14:46:39Z) - Deep Reinforcement Learning for Multi-class Imbalanced Training [64.9100301614621]
We introduce an imbalanced classification framework, based on reinforcement learning, for training extremely imbalanced data sets.
We formulate a custom reward function and episode-training procedure, specifically with the added capability of handling multi-class imbalanced training.
Using real-world clinical case studies, we demonstrate that our proposed framework outperforms current state-of-the-art imbalanced learning methods.
arXiv Detail & Related papers (2022-05-24T13:39:59Z) - CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep
Learning [55.733193075728096]
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance.
Sample re-weighting methods are popularly used to alleviate this data bias issue.
We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
arXiv Detail & Related papers (2022-02-11T13:49:51Z) - Balanced-MixUp for Highly Imbalanced Medical Image Classification [19.338350044289736]
We propose a novel mechanism for sampling training data based on the popular MixUp regularization technique.
We experiment with a highly imbalanced dataset of retinal images and a long-tail dataset of gastro-intestinal video frames.
arXiv Detail & Related papers (2021-09-20T21:31:31Z) - Long-Tailed Recognition Using Class-Balanced Experts [128.73438243408393]
We propose an ensemble of class-balanced experts that combines the strength of diverse classifiers.
Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition.
arXiv Detail & Related papers (2020-04-07T20:57:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.