Results 21 to 30 of about 9,759,453 (201)
Small Ship Detection of SAR Images Based on Optimized Feature Pyramid and Sample Augmentation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Synthetic aperture radar images have become the latest high-resolution imaging equipment, which can monitor the Earth 24 h a day. More and more deep-learning technologies are applied to ship target detection; however, in complex environments, due to the ...
Yicheng Gong +4 more
semanticscholar +1 more source
A Side-Scan Sonar Image Synthesis Method Based on a Diffusion Model
Journal of Marine Science and Engineering, 2023 The limited number and under-representation of side-scan sonar samples hinders the training of high-performance underwater object detection models. To address this issue, in this paper, we propose a diffusion model-based method to augment side-scan sonar
Zhiwei Yang +4 more
doaj +1 more source
Electronics, 2023 Machine vision is essential for intelligent industrial manufacturing driven by Industry 4.0, especially for surface defect detection of industrial products.
Jiaxing Yang +4 more
semanticscholar +1 more source
Augmented Negative Sampling for Collaborative Filtering
Proceedings of the 17th ACM Conference on Recommender Systems, 2023 Negative sampling is essential for implicit-feedback-based collaborative filtering, which is used to constitute negative signals from massive unlabeled data to guide supervised learning. The state-of-the-art idea is to utilize hard negative samples that carry more useful information to form a better decision boundary.
Yuhan Zhao +5 more
openaire +2 more sources
GIScience & Remote Sensing, 2023 Rapeseed mapping is important for national food security and government regulation of land use. Various methods, including empirical index-based and machine learning-based methods, have been developed to identify rapeseed using remote sensing.
Yunze Zang +8 more
doaj +1 more source
Remote Sensing, 2023 With the widespread application and functional complexity of deep neural networks (DNNs), the demand for training samples is increasing. This elevated requirement also extends to DNN-based SAR object detection.
Yi Kuang +4 more
doaj +1 more source
, 2022 Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the information encoded by that DA? How does the augmentation policy impact the final parameters of a model?
Balestriero, Randall +2 more
openaire +2 more sources
Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning [PDF]
Neural Information Processing Systems, 2023 Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra auxiliary ...
Guozheng Ma +8 more
semanticscholar +1 more source
Frontiers in Neuroscience, 2023 IntroductionDue to the lack of devices and the difficulty of gathering patients, the small sample size is one of the most challenging problems in functional brain network (FBN) analysis.
Qinghua Liu +3 more
doaj +1 more source
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning [PDF]
IEEE International Conference on Computer Vision, 2023 In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high confidence, resulting ...
Guan Gui +5 more
semanticscholar +1 more source