English
Related papers

Related papers: Generalization Gap in Data Augmentation: Insights …

200 papers

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…

Data augmentation is widely recognized for improving generalization in deep networks, yet its impact on the geometry of learned representations remains poorly understood. In this work, we characterize how different data augmentation…

Machine Learning · Computer Science 2026-05-18 Tianxiao He , Alex H. Williams , Sarah E. Harvey

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Dimitrios Sakkos , Hubert P. H. Shum , Edmond S. L. Ho

This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility.…

Machine Learning · Computer Science 2024-12-17 Ahmad Hassanpour , Amir Zarei , Khawla Mallat , Anderson Santana de Oliveira , Bian Yang

The use of synthetic data for training computer vision algorithms has become increasingly popular due to its cost-effectiveness, scalability, and ability to provide accurate multi-modality labels. Although recent studies have demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Eli Friedman , Assaf Lehr , Alexey Gruzdev , Vladimir Loginov , Max Kogan , Moran Rubin , Orly Zvitia

Data distortion is commonly applied in vision models during both training (e.g methods like MixUp and CutMix) and evaluation (e.g. shape-texture bias and robustness). This data modification can introduce artificial information. It is often…

Machine Learning · Computer Science 2022-07-07 Antonia Marcu , Adam Prügel-Bennett

Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical…

Machine Learning · Statistics 2020-11-10 Shuxiao Chen , Edgar Dobriban , Jane H Lee

In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…

Computer Vision and Pattern Recognition · Computer Science 2020-11-06 SeulGi Hong , Heonjin Ha , Junmo Kim , Min-Kook Choi

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Yang Shu , Zhangjie Cao , Chenyu Wang , Jianmin Wang , Mingsheng Long

Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation and hence is more robust to distribution shift. Data augmentation and equivariant…

Machine Learning · Computer Science 2022-06-22 Rui Wang , Robin Walters , Rose Yu

Several studies indicate that deep learning models can learn to detect breast cancer from mammograms (X-ray images of the breasts). However, challenges with overfitting and poor generalisability prevent their routine use in the clinic.…

Image and Video Processing · Electrical Eng. & Systems 2025-02-05 Emir Ahmed , Spencer A. Thomas , Ciaran Bench

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Machine Learning · Computer Science 2021-10-26 Jungsoo Lee , Eungyeup Kim , Juyoung Lee , Jihyeon Lee , Jaegul Choo

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

Computer Vision and Pattern Recognition · Computer Science 2014-02-18 Alexey Dosovitskiy , Jost Tobias Springenberg , Thomas Brox

The rapid progress in machine learning methods has been empowered by i) huge datasets that have been collected and annotated, ii) improved engineering (e.g. data pre-processing/normalization). The existing datasets typically include several…

Computer Vision and Pattern Recognition · Computer Science 2018-01-23 Grigorios G. Chrysos , Yannis Panagakis , Stefanos Zafeiriou

In this work, we propose data augmentation via pairwise mixup across subgroups to improve group fairness. Many real-world applications of machine learning systems exhibit biases across certain groups due to under-representation or training…

Machine Learning · Statistics 2023-09-14 Madeline Navarro , Camille Little , Genevera I. Allen , Santiago Segarra

Despite the clear performance benefits of data augmentations, little is known about why they are so effective. In this paper, we disentangle several key mechanisms through which data augmentations operate. Establishing an exchange rate…

Machine Learning · Computer Science 2023-04-03 Jonas Geiping , Micah Goldblum , Gowthami Somepalli , Ravid Shwartz-Ziv , Tom Goldstein , Andrew Gordon Wilson

Data augmentation that introduces diversity into the input data has long been used in training deep learning models. It has demonstrated benefits in improving robustness and generalization, practically aligning well with other…

Machine Learning · Computer Science 2025-08-18 Yang Ba , Michelle V. Mancenido , Rong Pan

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…

In this paper, we reveal the two sides of data augmentation: enhancements in closed-set recognition correlate with a significant decrease in open-set recognition. Through empirical investigation, we find that multi-sample-based…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Yunbing Jia , Xiaoyu Kong , Fan Tang , Yixing Gao , Weiming Dong , Yi Yang

Simple data augmentation techniques, such as rotations and flips, are widely used to enhance the generalization power of computer vision models. However, these techniques often fail to modify high-level semantic attributes of a class. To…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Tobias Lingenberg , Markus Reuter , Gopika Sudhakaran , Dominik Gojny , Stefan Roth , Simone Schaub-Meyer