English
Related papers

Related papers: FMix: Enhancing Mixed Sample Data Augmentation

200 papers

Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 JongMok Kim , Jooyoung Jang , Seunghyeon Seo , Jisoo Jeong , Jongkeun Na , Nojun Kwak

Data augmentation is widely utilized as an effective technique to enhance the generalization performance of deep models. However, data augmentation may inevitably introduce distribution shifts and noises, which significantly constrain the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Suorong Yang , Hongchao Yang , Suhan Guo , Furao Shen , Jian Zhao

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Muzhou Yu , Linfeng Zhang , Kaisheng Ma

Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout strategies have…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Arjon Das , Xin Zhong

Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting and enhance their generalization and performance, various methods have been suggested in the literature, including dropout, regularization, label…

Computer Vision and Pattern Recognition · Computer Science 2023-02-08 Humza Naveed , Saeed Anwar , Munawar Hayat , Kashif Javed , Ajmal Mian

In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…

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…

Machine Learning · Computer Science 2025-05-13 Suorong Yang , Peng Ye , Furao Shen , Dongzhan Zhou

Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Haijian Chen , Wendong Zhang , Yunbo Wang , Xiaokang Yang

Training deep neural networks requires datasets with a large number of annotated examples. The collection and annotation of these datasets is not only extremely expensive but also faces legal and privacy problems. These factors are a…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Christoph Reinders , Frederik Schubert , Bodo Rosenhahn

Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning. Specific augmentations like translations and scaling in computer vision are traditionally believed to improve generalization by generating…

Machine Learning · Computer Science 2024-02-29 Chi-Heng Lin , Chiraag Kaushik , Eva L. Dyer , Vidya Muthukumar

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xin Jin , Siyuan Li , Siyong Jian , Kai Yu , Huan Wang

Federated learning (FL) enables multiple client medical institutes collaboratively train a deep learning (DL) model with privacy protection. However, the performance of FL can be constrained by the limited availability of labeled data in…

Image and Video Processing · Electrical Eng. & Systems 2023-10-25 Yongsong Huang , Wanqing Xie , Mingzhen Li , Mingmei Cheng , Jinzhou Wu , Weixiao Wang , Jane You , Xiaofeng Liu

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…

Machine Learning · Computer Science 2024-11-06 Muthu Chidambaram , Xiang Wang , Chenwei Wu , Rong Ge

The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scale computational…

Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the performance and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Hao Zhang , Shuaijie Zhang , Renbin Zou

Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Dominik Lewy , Jacek Mańdziuk

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Suorong Yang , Peijia Li , Xin Xiong , Furao Shen , Jian Zhao

Machine Learning (ML) has emerged as a core technology to provide learning models to perform complex tasks. Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever increasing. However,…

Machine Learning · Computer Science 2024-03-04 Antoine Boutet , Thomas Lebrun , Jan Aalmoes , Adrien Baud

Background: Medical images are more difficult to acquire and annotate than natural images, which results in data augmentation technologies often being used in medical image segmentation tasks. Most data augmentation technologies used in…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Lianting Hu , Huiying Liang , Jiajie Tang , Xin Li , Li Huang , Long Lu

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Deepan Das , Haley Massa , Abhimanyu Kulkarni , Theodoros Rekatsinas