Zobrazeno 1 - 10
of 426
pro vyhledávání: '"Zhang, Zhongyue"'
The focus on dark matter search has expanded to include low-mass particles such as axions or axion-like particles, and novel theoretical schemes extending the phenomenological landscape, within QCD and beyond, also garnered additional interest in rec
Externí odkaz:
http://arxiv.org/abs/2111.04541
Autor:
Zhu, Yi, Zhang, Zhongyue, Wu, Chongruo, Zhang, Zhi, He, Tong, Zhang, Hang, Manmatha, R., Li, Mu, Smola, Alexander
Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain s
Externí odkaz:
http://arxiv.org/abs/2004.14960
Autor:
Zhang, Hang, Wu, Chongruo, Zhang, Zhongyue, Zhu, Yi, Lin, Haibin, Zhang, Zhi, Sun, Yue, He, Tong, Mueller, Jonas, Manmatha, R., Li, Mu, Smola, Alexander
It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage th
Externí odkaz:
http://arxiv.org/abs/2004.08955
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Guo, Jian, He, He, He, Tong, Lausen, Leonard, Li, Mu, Lin, Haibin, Shi, Xingjian, Wang, Chenguang, Xie, Junyuan, Zha, Sheng, Zhang, Aston, Zhang, Hang, Zhang, Zhi, Zhang, Zhongyue, Zheng, Shuai, Zhu, Yi
Publikováno v:
Journal of Machine Learning Research 21 (2020) 1-7
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to fa
Externí odkaz:
http://arxiv.org/abs/1907.04433
Synthesis planning is the process of recursively decomposing target molecules into available precursors. Computer-aided retrosynthesis can potentially assist chemists in designing synthetic routes, but at present it is cumbersome and provides results
Externí odkaz:
http://arxiv.org/abs/1907.01356
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}. Object detection models, however, have more complex neural network structures and optimization targets. The training strategies and pipelines dramatic
Externí odkaz:
http://arxiv.org/abs/1902.04103
Autor:
Cui, Pengfei, Huo, Yiping, Zhang, Zhongyue, Wang, Yunyan, Song, Meina, Zhao, Chen, Liu, Tong, Liao, Zuxiong
Publikováno v:
In Micro and Nanostructures March 2023 175
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly menti
Externí odkaz:
http://arxiv.org/abs/1812.01187
Publikováno v:
In Applied Surface Science 1 February 2023 610