Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Jiaolong Xu"'
Publikováno v:
Sensors, Vol 23, Iss 11, p 5273 (2023)
Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. Howev
Externí odkaz:
https://doaj.org/article/38851932cd0440d788b09ce8661e0a6a
Publikováno v:
IEEE Access, Vol 7, Pp 156694-156706 (2019)
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work,
Externí odkaz:
https://doaj.org/article/fcf4d56622dc46d480738a8462d81065
Autor:
Alejandro González, Zhijie Fang, Yainuvis Socarras, Joan Serrat, David Vázquez, Jiaolong Xu, Antonio M. López
Publikováno v:
Sensors, Vol 16, Iss 6, p 820 (2016)
Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, nam
Externí odkaz:
https://doaj.org/article/27e9814495684ca8998ce8597579e439
Publikováno v:
2022 International Conference on 3D Vision (3DV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d79bb576ad5619a374a82465190af5e6
https://doi.org/10.1109/3dv57658.2022.00020
https://doi.org/10.1109/3dv57658.2022.00020
Publikováno v:
IEEE Robotics and Automation Letters. 6:3445-3450
Deep learning has recently demonstrated its promising performance for vision-based parking-slot detection. However, very few existing methods explicitly take into account learning the link information of the marking-points, resulting in complex post-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::029ce763c416f7fda6214417a9bbb6c9
https://doi.org/10.1109/lra.2021.3064270
https://doi.org/10.1109/lra.2021.3064270
Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve the accuracy and robustness. H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9f885c44e1a4358fc4d0bb2418ef8ec
Publikováno v:
IEEE Access, Vol 7, Pp 156694-156706 (2019)
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::200a16be71f94662da574ee04c49052b
https://ieeexplore.ieee.org/document/8883232/
https://ieeexplore.ieee.org/document/8883232/
Publikováno v:
ICPR
We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a0157d86bf691b3357c81554b0d7e98
Publikováno v:
ICPR
Person re-identification (Re-ID) is an important technique for video surveillance and security systems. Most existing Re-ID methods assume fixed size of training data and the models have to be re-trained from scratch given newly collected data, which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b76e67516305c093dd61bcc7b4e609a
https://doi.org/10.1109/icpr.2018.8546301
https://doi.org/10.1109/icpr.2018.8546301
Publikováno v:
ICRA
Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87d9dbbb4ecf171323bca158ceae071d
http://arxiv.org/abs/1804.06332
http://arxiv.org/abs/1804.06332