Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Cheng, Shuyang"'
Autor:
Leng, Zhaoqi, Cheng, Shuyang, Caine, Benjamin, Wang, Weiyue, Zhang, Xiao, Shlens, Jonathon, Tan, Mingxing, Anguelov, Dragomir
Publikováno v:
ECCV 2022 (pp. 555-572). Springer, Cham
Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been designed to only utilize labeled data, which limits the data diversit
Externí odkaz:
http://arxiv.org/abs/2210.13428
Autor:
Wang, Gary, Cubuk, Ekin D., Rosenberg, Andrew, Cheng, Shuyang, Weiss, Ron J., Ramabhadran, Bhuvana, Moreno, Pedro J., Le, Quoc V., Park, Daniel S.
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has become automated and more "end-to-end", the data augmentation policy (what
Externí odkaz:
http://arxiv.org/abs/2210.10879
Autor:
Liu, Chenxi, Leng, Zhaoqi, Sun, Pei, Cheng, Shuyang, Qi, Charles R., Zhou, Yin, Tan, Mingxing, Anguelov, Dragomir
Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving. However, arguably due to the higher-dimensional nature of the data (as compared to images), existing neura
Externí odkaz:
http://arxiv.org/abs/2210.05018
Autor:
Leng, Zhaoqi, Tan, Mingxing, Liu, Chenxi, Cubuk, Ekin Dogus, Shi, Xiaojie, Cheng, Shuyang, Anguelov, Dragomir
Publikováno v:
International Conference on Learning Representations. 2021
Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for different
Externí odkaz:
http://arxiv.org/abs/2204.12511
Autor:
Ettinger, Scott, Cheng, Shuyang, Caine, Benjamin, Liu, Chenxi, Zhao, Hang, Pradhan, Sabeek, Chai, Yuning, Sapp, Ben, Qi, Charles, Zhou, Yin, Yang, Zoey, Chouard, Aurelien, Sun, Pei, Ngiam, Jiquan, Vasudevan, Vijay, McCauley, Alexander, Shlens, Jonathon, Anguelov, Dragomir
As autonomous driving systems mature, motion forecasting has received increasing attention as a critical requirement for planning. Of particular importance are interactive situations such as merges, unprotected turns, etc., where predicting individua
Externí odkaz:
http://arxiv.org/abs/2104.10133
Publikováno v:
In Cell Reports 23 January 2024 43(1)
Autor:
Stidham, Ryan W., Cai, Lingrui, Cheng, Shuyang, Rajaei, Flora, Hiatt, Tadd, Wittrup, Emily, Rice, Michael D., Bishu, Shrinivas, Wehkamp, Jan, Schultz, Weiwei, Khan, Najat, Stojmirovic, Aleksandar, Ghanem, Louis R., Najarian, Kayvan
Publikováno v:
In Gastroenterology January 2024 166(1):155-167
Autor:
Bender, Gabriel, Liu, Hanxiao, Chen, Bo, Chu, Grace, Cheng, Shuyang, Kindermans, Pieter-Jan, Le, Quoc
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 14323-14332
Efficient Neural Architecture Search methods based on weight sharing have shown good promise in democratizing Neural Architecture Search for computer vision models. There is, however, an ongoing debate whether these efficient methods are significantl
Externí odkaz:
http://arxiv.org/abs/2008.06120
Autor:
Cheng, Shuyang, Leng, Zhaoqi, Cubuk, Ekin Dogus, Zoph, Barret, Bai, Chunyan, Ngiam, Jiquan, Song, Yang, Caine, Benjamin, Vasudevan, Vijay, Li, Congcong, Le, Quoc V., Shlens, Jonathon, Anguelov, Dragomir
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:
http://arxiv.org/abs/2004.00831
Autor:
Cheng, Shuyang
In this paper, a Chaudouard type trace formula is established for the Lie algebra $\mathfrak{gl}(n)$, by integrating the Lie algebra analogue of the Selberg kernel function against a mirabolic Eisenstein series on $\mathrm{GL}(n)$. The result is a co
Externí odkaz:
http://arxiv.org/abs/2002.08906