Zobrazeno 1 - 10
of 207
pro vyhledávání: '"Zou, Yuliang"'
Autor:
Zou, Yuliang
Modern deep neural networks are proficient at solving various visual recognition and understanding tasks, as long as a sufficiently large labeled dataset is available during the training time. However, the progress of these visual tasks is limited by
Externí odkaz:
http://hdl.handle.net/10919/110313
Autor:
Luo, Zelun, Zou, Yuliang, Yang, Yijin, Durante, Zane, Huang, De-An, Yu, Zhiding, Xiao, Chaowei, Fei-Fei, Li, Anandkumar, Animashree
In recent years, differential privacy has seen significant advancements in image classification; however, its application to video activity recognition remains under-explored. This paper addresses the challenges of applying differential privacy to vi
Externí odkaz:
http://arxiv.org/abs/2306.15742
We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchNorm (statistics) calibration. Our approac
Externí odkaz:
http://arxiv.org/abs/2203.16530
Autor:
Chen, Shuohui, Wang, Junkai, zuo, Wenqiang, Du, Zhenxing, Zou, Yuliang, Li, Qiutong, Du, Fengyin, Du, Zhirong, Lu, Yucan, She, Wei
Publikováno v:
In Journal of Building Engineering 1 November 2024 96
Autor:
Shi, En, Zou, Yuliang, Zheng, Yunbin, Zhang, Miao, Liu, Shasha, Zhang, Shuai, Zhang, Xiangzhi
Publikováno v:
In Bioresource Technology July 2024 403
Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce. Constraining the model predictions to be invariant to diverse data augmentations effectively injects the desired representational invariances
Externí odkaz:
http://arxiv.org/abs/2103.16565
Autor:
Zou, Yuliang, Zhang, Zizhao, Zhang, Han, Li, Chun-Liang, Bian, Xiao, Huang, Jia-Bin, Pfister, Tomas
Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification, semantic segm
Externí odkaz:
http://arxiv.org/abs/2010.09713
We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this pap
Externí odkaz:
http://arxiv.org/abs/2008.11714
Monocular visual odometry (VO) suffers severely from error accumulation during frame-to-frame pose estimation. In this paper, we present a self-supervised learning method for VO with special consideration for consistency over longer sequences. To thi
Externí odkaz:
http://arxiv.org/abs/2007.10983
Publikováno v:
In Journal of Building Engineering 15 November 2023 79