Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Zhu, JiaPeng"'
The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approac
Externí odkaz:
http://arxiv.org/abs/2408.03195
Graph neural networks (GNNs) have demonstrated significant success in various applications, such as node classification, link prediction, and graph classification. Active learning for GNNs aims to query the valuable samples from the unlabeled data fo
Externí odkaz:
http://arxiv.org/abs/2402.10074
Generative Adversarial Networks (GANs) have significantly advanced image synthesis through mapping randomly sampled latent codes to high-fidelity synthesized images. However, applying well-trained GANs to real image editing remains challenging. A com
Externí odkaz:
http://arxiv.org/abs/2309.13956
Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution
Externí odkaz:
http://arxiv.org/abs/2309.03904
The success of style-based generators largely benefits from style modulation, which helps take care of the cross-instance variation within data. However, the instance-wise stochasticity is typically introduced via regular convolution, where kernels i
Externí odkaz:
http://arxiv.org/abs/2308.15472
Recent years witness the tremendous success of generative adversarial networks (GANs) in synthesizing photo-realistic images. GAN generator learns to compose realistic images and reproduce the real data distribution. Through that, a hierarchical visu
Externí odkaz:
http://arxiv.org/abs/2301.05315
This work presents an easy-to-use regularizer for GAN training, which helps explicitly link some axes of the latent space to a set of pixels in the synthesized image. Establishing such a connection facilitates a more convenient local control of GAN g
Externí odkaz:
http://arxiv.org/abs/2301.04604
Autor:
Ge, Jian, Zhang, Hui, Zang, Weicheng, Deng, Hongping, Mao, Shude, Xie, Ji-Wei, Liu, Hui-Gen, Zhou, Ji-Lin, Willis, Kevin, Huang, Chelsea, Howell, Steve B., Feng, Fabo, Zhu, Jiapeng, Yao, Xinyu, Liu, Beibei, Aizawa, Masataka, Zhu, Wei, Li, Ya-Ping, Ma, Bo, Ye, Quanzhi, Yu, Jie, Xiang, Maosheng, Yu, Cong, Liu, Shangfei, Yang, Ming, Wang, Mu-Tian, Shi, Xian, Fang, Tong, Zong, Weikai, Liu, Jinzhong, Zhang, Yu, Zhang, Liyun, El-Badry, Kareem, Shen, Rongfeng, Tam, Pak-Hin Thomas, Hu, Zhecheng, Yang, Yanlv, Zou, Yuan-Chuan, Wu, Jia-Li, Lei, Wei-Hua, Wei, Jun-Jie, Wu, Xue-Feng, Sun, Tian-Rui, Wang, Fa-Yin, Zhang, Bin-Bin, Xu, Dong, Yang, Yuan-Pei, Li, Wen-Xiong, Xiang, Dan-Feng, Wang, Xiaofeng, Wang, Tinggui, Zhang, Bing, Jia, Peng, Yuan, Haibo, Zhang, Jinghua, Wang, Sharon Xuesong, Gan, Tianjun, Wang, Wei, Zhao, Yinan, Liu, Yujuan, Wei, Chuanxin, Kang, Yanwu, Yang, Baoyu, Qi, Chao, Liu, Xiaohua, Zhang, Quan, Zhu, Yuji, Zhou, Dan, Zhang, Congcong, Yu, Yong, Zhang, Yongshuai, Li, Yan, Tang, Zhenghong, Wang, Chaoyan, Wang, Fengtao, Li, Wei, Cheng, Pengfei, Shen, Chao, Li, Baopeng, Pan, Yue, Yang, Sen, Gao, Wei, Song, Zongxi, Wang, Jian, Zhang, Hongfei, Chen, Cheng, Wang, Hui, Zhang, Jun, Wang, Zhiyue, Zeng, Feng, Zheng, Zhenhao, Zhu, Jie, Guo, Yingfan, Zhang, Yihao, Li, Yudong, Wen, Lin, Feng, Jie, Chen, Wen, Chen, Kun, Han, Xingbo, Yang, Yingquan, Wang, Haoyu, Duan, Xuliang, Huang, Jiangjiang, Liang, Hong, Bi, Shaolan, Gai, Ning, Ge, Zhishuai, Guo, Zhao, Huang, Yang, Li, Gang, Li, Haining, Li, Tanda, Yuxi, Lu, Rix, Hans-Walter, Shi, Jianrong, Song, Fen, Tang, Yanke, Ting, Yuan-Sen, Wu, Tao, Wu, Yaqian, Yang, Taozhi, Yin, Qing-Zhu, Gould, Andrew, Lee, Chung-Uk, Dong, Subo, Yee, Jennifer C., Shvartzvald, Yossi, Yang, Hongjing, Kuang, Renkun, Zhang, Jiyuan, Liao, Shilong, Qi, Zhaoxiang, Yang, Jun, Zhang, Ruisheng, Jiang, Chen, Ou, Jian-Wen, Li, Yaguang, Beck, Paul, Bedding, Timothy R., Campante, Tiago L., Chaplin, William J., Christensen-Dalsgaard, Jørgen, García, Rafael A., Gaulme, Patrick, Gizon, Laurent, Hekker, Saskia, Huber, Daniel, Khanna, Shourya, Mathur, Savita, Miglio, Andrea, Mosser, Benoît, Ong, J. M. Joel, Santos, Ângela R. G., Stello, Dennis, Bowman, Dominic M., Lares-Martiz, Mariel, Murphy, Simon, Niu, Jia-Shu, Ma, Xiao-Yu, Molnár, László, Fu, Jian-Ning, De Cat, Peter, Su, Jie, consortium, the ET
We propose to develop a wide-field and ultra-high-precision photometric survey mission, temporarily named "Earth 2.0 (ET)". This mission is designed to measure, for the first time, the occurrence rate and the orbital distributions of Earth-sized plan
Externí odkaz:
http://arxiv.org/abs/2206.06693
Understanding the mechanism of generative adversarial networks (GANs) helps us better use GANs for downstream applications. Existing efforts mainly target interpreting unconditional models, leaving it less explored how a conditional GAN learns to ren
Externí odkaz:
http://arxiv.org/abs/2203.11173
Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image editing tasks using pre-trained generators. Existing methods typically employ the latent space of GANs as the inversion space yet observe the insufficient recovery of
Externí odkaz:
http://arxiv.org/abs/2203.11105