Results 11 to 20 of about 598,648 (280)
Counterexample-Guided Data Augmentation [PDF]
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018 We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include
Dreossi, Tommaso +5 more
core +5 more sources
Data Augmentation for Text Generation Without Any Augmented Data [PDF]
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021 Accepted into the main conference of ACL ...
Wei Bi, Huayang Li, Jiacheng Huang 0005
openaire +2 more sources
Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data [PDF]
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021 Unsupervised Data Augmentation (UDA) is a semi-supervised technique that applies a consistency loss to penalize differences between a model's predictions on (a) observed (unlabeled) examples; and (b) corresponding 'noised' examples produced via data augmentation.
David Lowell +3 more
openaire +2 more sources
Advances in Neural Information Processing Systems 36, 2023 We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression. Our data augmentation algorithm borrows from the literature on causality and extends the recently proposed Anchor regression (AR) method for data augmentation, which is in contrast to the current state-of-the-art domain-agnostic solutions that rely on the ...
Nora Schneider +2 more
openaire +3 more sources
Data Augmentation for Manipulation
Robotics: Science and Systems XVIII, 2022 The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and expensive, and therefore learning from small datasets is an important open problem.
Peter Mitrano, Dmitry Berenson
openaire +2 more sources
Data Augmentation for Electrocardiograms
CoRR, 2022 Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not available for many predictive tasks of interest.
Aniruddh Raghu +4 more
openaire +3 more sources
A Data Augmentation Algorithm for Trajectory Data
Proceedings of the 1st ACM SIGSPATIAL International Workshop on Methods for Enriched Mobility Data: Emerging issues and Ethical perspectives 2023, 2023 The growing prevalence of location-based devices has resulted in a signi!cant abundance of location data from various tracking vendors. Nevertheless, a noticeable de!cit exists regarding readily accessible, extensive, and publicly available datasets for research purposes, primarily due to privacy concerns and ownership constraints.
J. Haranwala, Yaksh +3 more
openaire +3 more sources
Augmentation of adaptation data [PDF]
Interspeech 2010, 2010 Linear regression based speaker adaptation approaches can improve Automatic Speech Recognition (ASR) accuracy significantly for a target speaker. However, when the available adaptation data is limited to a few seconds, the accuracy of the speaker adapted models is often worse compared with speaker independent models.
Vipperla, Ravi Chander +2 more
openaire +3 more sources
Data Augmentation for Speech Separation
SSRN Electronic Journal, 2022 Deep learning models have advanced the state of the art of monaural speech separation. However, the performance of a separation model considerably decreases when tested on unseen speakers and noisy conditions. Separation models trained with data augmentation generalize better to unseen conditions.
Alex A. +3 more
openaire +2 more sources