Zobrazeno 1 - 10
of 269
pro vyhledávání: '"Liu, Weitang"'
Evaluating models on datasets often fails to capture their behavior when faced with unexpected and diverse types of inputs. It would be beneficial if we could evaluate the difference between human annotation and model prediction for an internet numbe
Externí odkaz:
http://arxiv.org/abs/2312.03291
State-of-the-art weakly supervised text classification methods, while significantly reduced the required human supervision, still requires the supervision to cover all the classes of interest. This is never easy to meet in practice when human explore
Externí odkaz:
http://arxiv.org/abs/2305.12401
The output distribution of a neural network (NN) over the entire input space captures the complete input-output mapping relationship, offering insights toward a more comprehensive NN understanding. Exhaustive enumeration or traditional Monte Carlo me
Externí odkaz:
http://arxiv.org/abs/2302.09484
Estimating out-of-distribution (OOD) uncertainty is a central challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detection in multi-class classification have emerged, while OOD detection met
Externí odkaz:
http://arxiv.org/abs/2109.14162
Autor:
Xu, Yaobin, Liu, Weitang, Jiang, Zhongyi, Xu, Zixuan, Mao, Tingyun, Chen, Lili, Zhou, Mingwei
Traffic forecasting is a core element of intelligent traffic monitoring system. Approaches based on graph neural networks have been widely used in this task to effectively capture spatial and temporal dependencies of road networks. However, these app
Externí odkaz:
http://arxiv.org/abs/2108.03594
Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident poster
Externí odkaz:
http://arxiv.org/abs/2010.03759
Autor:
Xu, Liang, Hu, Hai, Zhang, Xuanwei, Li, Lu, Cao, Chenjie, Li, Yudong, Xu, Yechen, Sun, Kai, Yu, Dian, Yu, Cong, Tian, Yin, Dong, Qianqian, Liu, Weitang, Shi, Bo, Cui, Yiming, Li, Junyi, Zeng, Jun, Wang, Rongzhao, Xie, Weijian, Li, Yanting, Patterson, Yina, Tian, Zuoyu, Zhang, Yiwen, Zhou, He, Liu, Shaoweihua, Zhao, Zhe, Zhao, Qipeng, Yue, Cong, Zhang, Xinrui, Yang, Zhengliang, Richardson, Kyle, Lan, Zhenzhong
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and a
Externí odkaz:
http://arxiv.org/abs/2004.05986
Autor:
Xu, Liang, tong, Yu, Dong, Qianqian, Liao, Yixuan, Yu, Cong, Tian, Yin, Liu, Weitang, Li, Lu, Liu, Caiquan, Zhang, Xuanwei
In this paper, we introduce the NER dataset from CLUE organization (CLUENER2020), a well-defined fine-grained dataset for named entity recognition in Chinese. CLUENER2020 contains 10 categories. Apart from common labels like person, organization, and
Externí odkaz:
http://arxiv.org/abs/2001.04351
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
In this paper, we propose a novel architecture that iteratively discovers and segments out the objects of a scene based on the image reconstruction quality. Different from other approaches, our model uses an explicit localization module that localize
Externí odkaz:
http://arxiv.org/abs/1911.09228