Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Barret Zoph"'
Autor:
Barret Zoph
Publikováno v:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::427f9be6c5b6268b3e533037a0fd9cc6
https://doi.org/10.1109/ipdpsw55747.2022.00171
https://doi.org/10.1109/ipdpsw55747.2022.00171
Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which harnesses th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c136368262e83d0b6c534f8b1f3c12c7
http://arxiv.org/abs/2108.11353
http://arxiv.org/abs/2108.11353
Autor:
Ekin D. Cubuk, Maxwell D. Collins, Bowen Cheng, Liang-Chieh Chen, Hartwig Adam, Barret Zoph, Raphael Gontijo Lopes, Jonathon Shlens
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585440
ECCV (9)
ECCV (9)
Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of supervised l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e874eca1af265a36e2b55de940f509f7
https://doi.org/10.1007/978-3-030-58545-7_40
https://doi.org/10.1007/978-3-030-58545-7_40
Autor:
Barret Zoph, Quoc V. Le, Yin Cui, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Rui Qian, Aravind Srinivas
Publikováno v:
CVPR
Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perfo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7c8647731bbf457fd5e52baab6c9f70
Autor:
Ekin D. Cubuk, Zhaoqi Leng, Chunyan Bai, Jonathon Shlens, Jiquan Ngiam, Vijay K. Vasudevan, Dragomir Anguelov, Shuyang Cheng, Barret Zoph, Benjamin Caine, Congcong Li, Quoc V. Le, Yang Song
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585884
ECCV (21)
ECCV (21)
Data augmentation has been widely adopted for object detection in 3D point clouds. However, all previous related efforts have focused on manually designing specific data augmentation methods for individual architectures. In this work, we present the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6459d7bd81253675ef7311ee28bbdf0c
https://doi.org/10.1007/978-3-030-58589-1_17
https://doi.org/10.1007/978-3-030-58589-1_17
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585822
ECCV (27)
ECCV (27)
Much research on object detection focuses on building better model architectures and detection algorithms. Changing the model architecture, however, comes at the cost of adding more complexity to inference, making models slower. Data augmentation, on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::99e18c59d4ecd324dc9ca14ddedc0864
https://doi.org/10.1007/978-3-030-58583-9_34
https://doi.org/10.1007/978-3-030-58583-9_34
Publikováno v:
ICCV
Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information. Self-attenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9765f95d2da94b8203d47f16ce39ff11
https://doi.org/10.1109/iccv.2019.00338
https://doi.org/10.1109/iccv.2019.00338
Publikováno v:
CVPR Workshops
Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1848cf87a37df4ab55171270de9bd28f
http://arxiv.org/abs/1909.13719
http://arxiv.org/abs/1909.13719
Publikováno v:
CVPR
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1494420b1617287d3d01acc5378ea30
https://doi.org/10.1109/cvpr.2019.00020
https://doi.org/10.1109/cvpr.2019.00020
Autor:
Yu Zhang, Daniel S. Park, Quoc V. Le, Chung-Cheng Chiu, Barret Zoph, William Chan, Ekin D. Cubuk
Publikováno v:
INTERSPEECH
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b38d70f291706e68ae7488c4655c9012
http://arxiv.org/abs/1904.08779
http://arxiv.org/abs/1904.08779