Adjusting Decision Boundary for Class Imbalanced Learning

Kim, Byungju; Kim, Junmo

doi:10.1109/access.2020.2991231

Cited by 53 publications

(43 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is usually the case that real-world data exhibit a imbalanced distribution, and highly skewed data can adversely affect the effectiveness of machine learning [10,3]. Re-sampling [11] and re-weighting [12,10,13] are traditional methods towards addressing imbalanced data. Through re-weighting strategies, modern works can make networks more sensitive to minority categories by assigning a variable weight to each class.…”

Section: Learning From Imbalanced Datamentioning

confidence: 99%

Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

Zhang¹,

Zhang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the performance of imbalanced learning. We provide a new perspective on how to deal with imbalanced data: adjust the biased decision boundary by training with Guiding Adversarial Examples (GAEs). Our method can effectively increase the accuracy of minority classes while sacrificing little accuracy on majority classes. We empirically show, on several benchmark datasets, our proposed method is comparable to the state-ofthe-art method. To our best knowledge, we are the first to deal with imbalanced learning with adversarial examples.

show abstract

Section: Learning From Imbalanced Datamentioning

confidence: 99%

Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

Zhang¹,

Zhang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Nevertheless, data resampling or loss function engineering will influence the representations of data (Ren et al 2020). Lots of empirical observations show that we can acquire good representation when using the standard training and the classifier head is the performance bottleneck (Kang et al 2019;Zhang et al 2021;Yu et al 2020;Kim and Kim 2020). To solve the above problem, decision boundary adjustment methods re-adjust the classifier head after the standard training (Kang et al 2019;Zhang et al 2021).…”

Section: Related Workmentioning

confidence: 99%

Margin Calibration for Long-Tailed Visual Recognition

Wang¹,

Zhang²,

Hou³

et al. 2021

Preprint

View full text Add to dashboard Cite

The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits (classification scores) and empirically observe the biased margins and the biased logits are positively correlated. We propose MARC, a simple yet effective MARgin Calibration function to dynamically calibrate the biased margins for unbiased logits. We validate MARC through extensive experiments on common long-tailed benchmarks including CIFAR-LT, ImageNet-LT, Places-LT, and iNaturalist-LT. Experimental results demonstrate that our MARC achieves favorable results on these benchmarks. In addition, MARC is extremely easy to implement with just three lines of code. We hope this simple method will motivate people to rethink the biased margins and biased logits in long-tailed visual recognition.

show abstract

“…in [36], the authors propose an adaptive loss function that assigns weights to samples (both labeled and unlabeled) based on their importance. For the same setting, the authors of [19] analyze the entropy of the softmax function output in order to draw better decision boundaries between different classes. An approach for dealing with noisy labels was proposed by [6], who used two stacked softmax layers with the latter denoted as "noise separation layer" and used to model the noise of the original classification.…”

Section: Semi-supervised Learning Using Neural Networkmentioning

confidence: 99%

A Meta Learning-Based Approach for Zero-Shot Co-Training

Zaks

Katz

2021

IEEE Access

View full text Add to dashboard Cite

The lack of labeled data is one of the main obstacles to the application of machine learning algorithms in a variety of domains. Semi-supervised learning, where additional samples are automatically labeled, is a common and cost-effective approach to address this challenge. A popular semi-supervised labeling approach is co-training, where two views of the data -achieved by the training of two learning models on different feature subsets -iteratively provide each other with additional newly-labeled samples. Despite being effective in many cases, existing co-training algorithms often suffer from low labeling accuracy and a heuristic sample-selection strategy that hurt their performance. We propose Co-training using Meta-learning (CoMet), a novel approach that addresses many of the shortcomings of existing cotraining methods. Instead of employing a greedy labeling approach of individual samples, CoMet evaluates batches of samples and is thus able to select samples that complement each other. Additionally, our approach employs a meta-learning approach that enables it to leverage insights from previously-evaluated datasets and apply these insights to other datasets. Extensive evaluation on 35 datasets shows CoMet significantly outperforms other leading co-training approaches, particularly when the amount of available labeled data is very small. Moreover, our analysis shows that CoMet's labeling accuracy and consistency of performance are also superior to those of existing approaches. Co-training, Semi-supervised learning, meta-learning INDEX TERMS

show abstract

Adjusting Decision Boundary for Class Imbalanced Learning

Cited by 53 publications

References 43 publications

Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

Margin Calibration for Long-Tailed Visual Recognition

A Meta Learning-Based Approach for Zero-Shot Co-Training

Contact Info

Product

Resources

About