paper-with-me

Papers

The Effects of Mixed Sample Data Augmentation are Class Dependent

2023-07-18 · Haeil Lee, Hansang Lee, Junmo Kim

Mixed Sample Data Augmentation (MSDA) techniques, such as Mixup, CutMix, and PuzzleMix, have been widely acknowledged for enhancing performance in a variety of tasks. A previous study reported the class dependency of traditional data augmentation (DA), where certain classes benefit disproportionately compared to others. This paper reveals a class dependent effect of MSDA, where some classes experience improved performance while others experience degraded performance. This research addresses the issue of class dependency in MSDA and proposes an algorithm to mitigate it. The approach involves training on a mixture of MSDA and non-MSDA data, which not only mitigates the negative impact on the affected classes, but also improves overall accuracy. Furthermore, we provide in-depth analysis and discussion of why MSDA introduced class dependencies and which classes are most likely to have them.

📄 PDF Abstract BibTeX arXiv:2307.09136

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
CutMix CutMix is an image data augmentation strategy. Instead of simply removing pixels as in Cutout, we replace the removed regions with…

Similar Papers 제목 키워드 기반

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability

2023-03-26 · Soyoun Won, Sung-Ho Bae, Seong Tae Kim

Data augmentation strategies are actively used when training deep neural networks (DNNs). Recent studies suggest that they are effective at various tasks. However, the effect of data augmentation on DNNs' interpretabilit…

Data Augmentation

Adversarial AutoMixup

2023-12-19 · Huafeng Qin, Xin Jin, Yun Jiang, Mounim A. El-Yacoubi 외

Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been …

Classificationimage-classificationImage Classification

Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features

2023-04-16 · Ke Song, Quan Xia, Guoqiang Liang, Zhaojie Chen 외

Non-exemplar class-incremental learning refers to classifying new and old classes without storing samples of old classes. Since only new class samples are available for optimization, it often occurs catastrophic forgetti…

class-incremental learningClass Incremental LearningIncremental Learning

RegMix: Data Mixing Augmentation for Regression

2021-06-07 · Seong-Hyeon Hwang, Steven Euijong Whang

Data augmentation is becoming essential for improving regression performance in critical applications including manufacturing, climate prediction, and finance. Existing techniques for data augmentation largely focus on c…

ClassificationData AugmentationMeta-Learningregression

MiAMix: Enhancing Image Classification through a Multi-stage Augmented Mixed Sample Data Augmentation Method

2023-08-05 · Wen Liang, Youzhi Liang, Jianguo Jia

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model genera…

Computational EfficiencyData AugmentationImage Augmentationimage-classification+1