Data Leverage References

← Back to browse

Tag: data-augmentation (5 references)

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning 2022 inproceedings

Yongchan Kwon, James Zou

Generalizes Data Shapley using Beta weighting functions, providing noise-reduced data valuation that better handles outliers and mislabeled data detection.

A Survey on Image Data Augmentation for Deep Learning 2019 article

Connor Shorten, Taghi M. Khoshgoftaar

Comprehensive survey of image data augmentation techniques for deep learning, covering geometric transformations, color space transforms, kernel filters, mixing images, random erasing, and neural style transfer approaches.

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features 2019 inproceedings

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo

Combines cutting and mixing: patches from one image replace regions in another, with labels mixed proportionally. Improves over Cutout by using cut pixels constructively rather than zeroing them out.

mixup: Beyond Empirical Risk Minimization 2018 inproceedings

Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz

Introduces mixup, a data augmentation technique that trains on convex combinations of input pairs and their labels. Simple, data-independent, and model-agnostic approach that improves generalization and robustness.

Improved Regularization of Convolutional Neural Networks with Cutout 2017 article

Terrance DeVries, Graham W. Taylor

Introduces Cutout, a regularization technique that randomly masks square regions of input images during training. Inspired by dropout but applied to inputs, encouraging models to learn from partially visible objects.