中文
相关论文

相关论文: Automatic Data Augmentation by Learning the Determ…

200 篇论文

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

机器学习 · 计算机科学 2019-03-04 Michael Kuchnik , Virginia Smith

It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result. To that end, the community has…

机器学习 · 计算机科学 2023-07-17 Xiaomeng Dong , Michael Potter , Gaurav Kumar , Yun-Chan Tsai , V. Ratna Saripalli , Theodore Trafalis

Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. Existing work…

计算机视觉与模式识别 · 计算机科学 2021-11-02 Misgana Negassi , Diane Wagner , Alexander Reiterer

Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks. However, in most cases, data augmentation is randomly performed for each training sample with a certain probability, which might incur…

计算机视觉与模式识别 · 计算机科学 2021-12-07 Shiqi Lin , Zhizheng Zhang , Xin Li , Wenjun Zeng , Zhibo Chen

Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to…

计算机视觉与模式识别 · 计算机科学 2023-04-21 Mingjun Zhao , Shan Lu , Zixuan Wang , Xiaoli Wang , Di Niu

Data augmentation is an effective and universal technique for improving generalization performance of deep neural networks. It could enrich diversity of training samples that is essential in medical image segmentation tasks because 1) the…

图像与视频处理 · 电气工程与系统科学 2020-12-29 Ju Xu , Mengzhang Li , Zhanxing Zhu

Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of…

机器学习 · 计算机科学 2021-07-14 Ya Wang , Hesen Chen , Fangyi Zhang , Yaohua Wang , Xiuyu Sun , Ming Lin , Hao Li

In many classification problems, we want a classifier that is robust to a range of non-semantic transformations. For example, a human can identify a dog in a picture regardless of the orientation and pose in which it appears. There is…

机器学习 · 计算机科学 2021-12-20 Scott Mahan , Tim Doster , Henry Kvinge

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

机器学习 · 计算机科学 2017-08-22 Luke Taylor , Geoff Nitschke

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

机器人学 · 计算机科学 2022-07-21 Peter Mitrano , Dmitry Berenson

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

机器学习 · 计算机科学 2025-05-13 Suorong Yang , Peng Ye , Furao Shen , Dongzhan Zhou

Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…

计算机视觉与模式识别 · 计算机科学 2023-03-14 Teerath Kumar , Alessandra Mileo , Rob Brennan , Malika Bendechache

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Ant Duru , Alptekin Temizel

Medical image data are often limited due to the expensive acquisition and annotation process. Hence, training a deep-learning model with only raw data can easily lead to overfitting. One solution to this problem is to augment the raw data…

图像与视频处理 · 电气工程与系统科学 2023-12-19 Xinyue Xu , Yuhan Hsi , Haonan Wang , Xiaomeng Li

Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the automated data…

计算机视觉与模式识别 · 计算机科学 2021-08-13 Zirui Liu , Haifeng Jin , Ting-Hsiang Wang , Kaixiong Zhou , Xia Hu

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

机器学习 · 统计学 2025-01-16 Shulei Wang

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been…

计算机视觉与模式识别 · 计算机科学 2018-04-17 Yalong Bai , Kuiyuan Yang , Tao Mei , Wei-Ying Ma , Tiejun Zhao

Data augmentation reduces the generalization error by forcing a model to learn invariant representations given different transformations of the input image. In computer vision, on top of the standard image processing functions, data…

计算机视觉与模式识别 · 计算机科学 2021-10-22 Rowel Atienza

In recent years, one of the most popular techniques in the computer vision community has been the deep learning technique. As a data-driven technique, deep model requires enormous amounts of accurately labelled training data, which is often…

计算机视觉与模式识别 · 计算机科学 2022-10-10 Zihan Yang , Richard O. Sinnott , James Bailey , Qiuhong Ke

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

计算机视觉与模式识别 · 计算机科学 2017-12-14 Luis Perez , Jason Wang