English
Related papers

Related papers: PhysAug: A Physical-guided and Frequency-based Dat…

200 papers

Monocular 3D object detection (Mono3D) has achieved tremendous improvements with emerging large-scale autonomous driving datasets and the rapid development of deep learning techniques. However, caused by severe domain gaps (e.g., the field…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Zhenyu Li , Zehui Chen , Ang Li , Liangji Fang , Qinhong Jiang , Xianming Liu , Junjun Jiang

Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for Object Detection in space applications are often trained on…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Samet Hicsonmez , Abd El Rahman Shabayek , Arunkumar Rathinam , Djamila Aouada

Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that…

Machine Learning · Computer Science 2024-07-17 Abdulaziz Almuzairee , Nicklas Hansen , Henrik I. Christensen

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Federico Girella , Ziyue Liu , Franco Fummi , Francesco Setti , Marco Cristani , Luigi Capogrosso

This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Haixing Dai , Chong Ma , Zhiling Yan , Zhengliang Liu , Enze Shi , Yiwei Li , Peng Shu , Xiaozheng Wei , Lin Zhao , Zihao Wu , Fang Zeng , Dajiang Zhu , Wei Liu , Quanzheng Li , Lichao Sun , Shu Zhang Tianming Liu , Xiang Li

Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation policy may have different…

Computer Vision and Pattern Recognition · Computer Science 2023-10-04 Chengkai Hou , Jieyu Zhang , Tianyi Zhou

Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation have shown promise,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Mengzhu Wang , Changyuan Deng , Shanshan Wang , Nan Yin , Long Lan , Liang Yang

Transformers, particularly Vision Transformers (ViTs), have achieved state-of-the-art performance in large-scale image classification. However, they often require large amounts of data and can exhibit biases, such as center or size bias,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Tobias Christian Nauen , Brian Moser , Federico Raue , Stanislav Frolov , Andreas Dengel

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Guangtao Zheng , Mengdi Huai , Aidong Zhang

In recent years, there has been tremendous progress in object detection performance. However, despite these advances, the detection performance for small objects is significantly inferior to that of large objects. Detecting small objects is…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 DaeEun Yoon , Semin Kim , SangWook Yoo , Jongha Lee

Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have access to unlabeled…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Manuel Schwonberg , Fadoua El Bouazati , Nico M. Schmidt , Hanno Gottschalk

Detection of rare objects (e.g., traffic cones, traffic barrels and traffic warning triangles) is an important perception task to improve the safety of autonomous driving. Training of such models typically requires a large number of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Naifan Li , Fan Song , Ying Zhang , Pengpeng Liang , Erkang Cheng

Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Petr Šebek , Šimon Pokorný , Patrik Vacek , Tomáš Svoboda

Data augmentation is a popular tool for single source domain generalization, which expands the source domain by generating simulated ones, improving generalization on unseen target domains. In this work, we show that the performance of such…

Machine Learning · Computer Science 2025-05-20 Dong Kyu Cho , Inwoo Hwang , Sanghack Lee

Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for…

Machine Learning · Computer Science 2023-03-01 Youzhi Luo , Michael McThrow , Wing Yee Au , Tao Komikado , Kanji Uchino , Koji Maruhashi , Shuiwang Ji

The annotation of blind image quality assessment (BIQA) is labor-intensive and time-consuming, especially for authentic images. Training on synthetic data is expected to be beneficial, but synthetically trained models often suffer from poor…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Aobo Li , Jinjian Wu , Yongxu Liu , Leida Li

For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data. As a widely used data augmentation method, GT-sample effectively improves detection…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Xuzhong Hu , Zaipeng Duan , Jie Ma

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…

Image and Video Processing · Electrical Eng. & Systems 2020-12-29 Ju Xu , Mengzhang Li , Zhanxing Zhu

In this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Daniel V. Ruiz , Bruno A. Krinski , Eduardo Todt

Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant…