Results 21 to 30 of about 116,076 (264)
Mixed Sample Augmentation for Online Distillation
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023 Mixed Sample Regularization (MSR), such as MixUp or CutMix, is a powerful data augmentation strategy to generalize convolutional neural networks. Previous empirical analysis has illustrated an orthogonal performance gain between MSR and conventional offline Knowledge Distillation (KD).
Yiqing Shen 0003 +4 more
openaire +2 more sources
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
Reject inference, augmentation, and sample selection [PDF]
European Journal of Operational Research, 2007 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Banasik, John, Crook, Jonathan
openaire +2 more sources
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 0001 +5 more
openaire +2 more sources
Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation
Algorithms, 2022 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. The existing work focuses on image classification and object detection, whereas we provide the first study on semantic image ...
Misgana Negassi +2 more
openaire +4 more sources
CoRR, 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?
Randall Balestriero +2 more
openaire +2 more sources
Data Augmentation with Variational Autoencoders and Manifold Sampling [PDF]
, 2021 We propose a new efficient way to sample from a Variational Autoencoder in the challenging low sample size setting. This method reveals particularly well suited to perform data augmentation in such a low data regime and is validated across various standard and real-life data sets.
Chadebec, Clément +1 more
openaire +3 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
Sample Efficiency of Data Augmentation Consistency Regularization
CoRR, 2022 Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to use augmented data. In this paper, we take a step in this direction - we first present a simple and novel analysis for linear regression with label invariant augmentations ...
Shuo Yang +5 more
openaire +3 more sources
Sequence-Level Mixed Sample Data Augmentation [PDF]
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020 EMNLP ...
Demi Guo, Yoon Kim, Alexander M. Rush
openaire +2 more sources