paper-with-me

Papers

A Survey on Mixup Augmentations and Beyond

2024-09-08 · Xin Jin, Hongyu Zhu, Siyuan Li, Zedong Wang, Zicheng Liu, Chang Yu, Huafeng Qin, Stan Z. Li

As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at \url{https://github.com/Westlake-AI/Awesome-Mixup}.

📄 PDF Abstract BibTeX arXiv:2409.05202

Code (1)

Westlake-AI/Awesome-Mixup 공식 구현 pytorch

Tasks

Image ClassificationSelf-Supervised LearningSurvey

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
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:…

Similar Papers 제목 키워드 기반

Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond

2023-03-18 · Thanh Vu, Baochen Sun, Bodi Yuan, Alex Ngai 외

The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreg…

Domain Adaptationimage-classificationImage ClassificationObject+3

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

2021-03-02 · Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl 외

Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes …

Data Poisoning

Reducing Labelled Data Requirement for Pneumonia Segmentation using Image Augmentations

2021-02-25 · Jitesh Seth, Rohit Lokwani, Viraj Kulkarni, Aniruddha Pant 외

Deep learning semantic segmentation algorithms can localise abnormalities or opacities from chest radiographs. However, the task of collecting and annotating training data is expensive and requires expertise which remain…

Image AugmentationPneumonia DetectionSegmentationSemantic Segmentation

Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers

2024-05-23 · Bum Jun Kim, Sang Woo Kim

Vision transformers (ViTs) have demonstrated remarkable performance in a variety of vision tasks. Despite their promising capabilities, training a ViT requires a large amount of diverse data. Several studies empirically …

Data Augmentation

Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data

2023-09-18 · Peikun Guo, Huiyuan Yang, Akane Sano

Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invarian…

Data AugmentationTime SeriesTime Series Classification