English
Related papers

Related papers: Toward Understanding Generative Data Augmentation

200 papers

Data augmentation as a technique can mitigate data scarcity in machine learning. However, owing to fundamental differences in wireless data structures, traditional data augmentation techniques may not be suitable for wireless data.…

Networking and Internet Architecture · Computer Science 2025-09-11 Jinbo Wen , Jiawen Kang , Dusit Niyato , Yang Zhang , Jiacheng Wang , Biplab Sikdar , Ping Zhang

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

Machine Learning · Computer Science 2020-11-06 Calvin Luo , Hossein Mobahi , Samy Bengio

Data limitation is one of the most common issues in training machine learning classifiers for medical applications. Due to ethical concerns and data privacy, the number of people that can be recruited to such experiments is generally…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-14 Bahman Mirheidari , Yilin Pan , Daniel Blackburn , Ronan O'Malley , Traci Walker , Annalena Venneri , Markus Reuber , Heidi Christensen

Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions. In the context of Question Answering, work on domain adaptation methods…

Computation and Language · Computer Science 2024-02-12 Arijit Ghosh Chowdhury , Aman Chadha

Data sparsity is one of the key challenges associated with model development in Natural Language Understanding (NLU) for conversational agents. The challenge is made more complex by the demand for high quality annotated utterances commonly…

Computation and Language · Computer Science 2020-12-11 Olga Golovneva , Charith Peris

We study the effect of high-order statistics of data on the learning dynamics of neural networks (NNs) by using a moment-controllable non-Gaussian data model. Considering the expressivity of two-layer neural networks, we first construct the…

Machine Learning · Statistics 2026-02-03 Onat Ure , Samet Demir , Zafer Dogan

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Fazle Rahat , M Shifat Hossain , Md Rubel Ahmed , Sumit Kumar Jha , Rickard Ewetz

In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Haowen Wang , Guowei Zhang , Xiang Zhang , Zeyuan Chen , Haiyang Xu , Dou Hoon Kwark , Zhuowen Tu

Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require costly manual annotation, limiting their data scale. Models…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Chengxiang Fan , Muzhi Zhu , Hao Chen , Yang Liu , Weijia Wu , Huaqi Zhang , Chunhua Shen

Sequential data in industrial applications can be used to train and evaluate machine learning models (e.g. classifiers). Since gathering representative amounts of data is difficult and time consuming, there is an incentive to generate it…

Machine Learning · Computer Science 2021-01-14 Maximilian Ernst Tschuchnig , Cornelia Ferner , Stefan Wegenkittl

The success of large generative models has driven a paradigm shift, leveraging massive multi-source data to enhance model capabilities. However, the interaction among these sources remains theoretically underexplored. This paper takes the…

Machine Learning · Computer Science 2025-07-09 Rongzhen Wang , Yan Zhang , Chenyu Zheng , Chongxuan Li , Guoqiang Wu

The number of credit card fraud has been growing as technology grows and people can take advantage of it. Therefore, it is very important to implement a robust and effective method to detect such frauds. The machine learning algorithms are…

Machine Learning · Computer Science 2022-06-14 Sairamvinay Vijayaraghavan , Terry Guan , Jason , Song

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…

Information Retrieval · Computer Science 2023-11-28 Abhijit Anand , Jurek Leonhardt , Jaspreet Singh , Koustav Rudra , Avishek Anand

Random data augmentation is a critical technique to avoid overfitting in training deep neural network models. However, data augmentation and network training are usually treated as two isolated processes, limiting the effectiveness of…

Computer Vision and Pattern Recognition · Computer Science 2018-05-25 Xi Peng , Zhiqiang Tang , Fei Yang , Rogerio Feris , Dimitris Metaxas

Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating diverse samples.…

Machine Learning · Computer Science 2024-10-02 Vahid Jebraeeli , Bo Jiang , Hamid Krim , Derya Cansever

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Machine Learning · Computer Science 2021-03-29 Dafni Antotsiou , Carlo Ciliberto , Tae-Kyun Kim

There is a common belief that the successful training of deep neural networks requires many annotated training samples, which are often expensive and difficult to obtain especially in the biomedical imaging field. While it is often easy for…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Tony C. W Mok , Albert C. S Chung

Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation…

Machine Learning · Statistics 2018-05-18 Guillermo L. Grinblat , Lucas C. Uzal , Pablo M. Granitto

Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data changes throughout the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Wentian Zhang , Haozhe Liu , Bing Li , Jinheng Xie , Yawen Huang , Yuexiang Li , Yefeng Zheng , Bernard Ghanem