Zobrazeno 1 - 10
of 227
pro vyhledávání: '"Huang, Haiwen"'
Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked in existi
Externí odkaz:
http://arxiv.org/abs/2403.09593
The voluminous nature of geospatial temporal data from physical monitors and simulation models poses challenges to efficient data access, often resulting in cumbersome temporal selection experiences in web-based data portals. Thus, selecting a subset
Externí odkaz:
http://arxiv.org/abs/2403.03449
We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training classes and o
Externí odkaz:
http://arxiv.org/abs/2212.11720
Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using "out-of-distribution" (OoD) detection, that is, distinguishing between the training data distribution and an unseen
Externí odkaz:
http://arxiv.org/abs/2112.00856
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quantification in neural models. We show that theoretical justifications f
Externí odkaz:
http://arxiv.org/abs/2106.02469
Out-of-Distribution (OoD) detection is important for building safe artificial intelligence systems. However, current OoD detection methods still cannot meet the performance requirements for practical deployment. In this paper, we propose a simple yet
Externí odkaz:
http://arxiv.org/abs/2011.14654
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory" in Adam-like algorithms,
Externí odkaz:
http://arxiv.org/abs/1805.07557
Autor:
Zhang, Bo, Tan, Yunpeng, Wang, Hui, Zhang, Zheng, Zhou, Xiuzhuang, Wu, Jingyun, Mi, Yue, Huang, Haiwen, Wang, Wendong
Publikováno v:
In Pattern Recognition October 2022 130
Autor:
Ma, Zibo, Mi, Yue, Zhang, Bo, Zhang, Zheng, Bai, Yu, Wu, Jingyun, Huang, Haiwen, Wang, Wendong
Publikováno v:
Multimedia Tools & Applications; Sep2024, Vol. 83 Issue 29, p73507-73532, 26p