Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Huo, Xinyue"'
Autor:
Huo, Xinyue, Gu, Ran
The unconstrained binary quadratic programming (UBQP) problem is a class of problems of significant importance in many practical applications, such as in combinatorial optimization, circuit design, and other fields. The positive semidefinite penalty
Externí odkaz:
http://arxiv.org/abs/2408.04875
Autor:
Chen, Pengfei, Xie, Lingxi, Huo, Xinyue, Yu, Xuehui, Zhang, Xiaopeng, Sun, Yingfei, Han, Zhenjun, Tian, Qi
The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types
Externí odkaz:
http://arxiv.org/abs/2407.16682
Adapting Large Language Models (LLMs) for recommendation requires careful consideration of the decoding process, given the inherent differences between generating items and natural language. Existing approaches often directly apply LLMs' original dec
Externí odkaz:
http://arxiv.org/abs/2406.14900
We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the labeled images in the source do
Externí odkaz:
http://arxiv.org/abs/2303.09083
Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align with the target-doma
Externí odkaz:
http://arxiv.org/abs/2204.02684
Autor:
Huo, Xinyue, Xie, Lingxi, Wei, Longhui, Zhang, Xiaopeng, Li, Hao, Yang, Zijie, Zhou, Wengang, Li, Houqiang, Tian, Qi
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents heterogeneous contrast
Externí odkaz:
http://arxiv.org/abs/2011.09941
In medical image analysis, semi-supervised learning is an effective method to extract knowledge from a small amount of labeled data and a large amount of unlabeled data. This paper focuses on a popular pipeline known as self learning, and points out
Externí odkaz:
http://arxiv.org/abs/2006.13461
Publikováno v:
International Journal of Computer Vision; Sep2024, Vol. 132 Issue 9, p3954-3976, 23p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Building and Environment February 2020 169