Zobrazeno 1 - 10
of 953
pro vyhledávání: '"Wang, Xixi"'
Segment Anything Model (SAM) has recently achieved amazing results in the field of natural image segmentation. However, it is not effective for medical image segmentation, owing to the large domain gap between natural and medical images. In this pape
Externí odkaz:
http://arxiv.org/abs/2404.14837
Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by enhancing the
Externí odkaz:
http://arxiv.org/abs/2310.11417
Exploring sample relationships within each mini-batch has shown great potential for learning image representations. Existing works generally adopt the regular Transformer to model the visual content relationships, ignoring the cues of semantic/label
Externí odkaz:
http://arxiv.org/abs/2211.10622
Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to learn (1) con
Externí odkaz:
http://arxiv.org/abs/2208.12398
Autor:
Wang, Xixi1,2 (AUTHOR), Wang, Yanfei1,2 (AUTHOR), Chen, Jing1,2 (AUTHOR), Wang, Qinyao1,2 (AUTHOR), Liu, Zhongjian1 (AUTHOR), Yin, Yijie1,2 (AUTHOR), Yang, Tonghua3 (AUTHOR), Shen, Tao4 (AUTHOR), Sa, Yalian2 (AUTHOR) sayalian@126.com
Publikováno v:
Scientific Reports. 5/2/2024, Vol. 14 Issue 1, p1-14. 14p.
Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either adopt the C
Externí odkaz:
http://arxiv.org/abs/2112.01177
Autor:
Cheng, Jiao, Yuan, Lin, Yu, Shuwen, Gu, Bing, Luo, Qian, Wang, Xixi, Zhao, Yijing, Gai, Chengcheng, Li, Tingting, Liu, Weiyang, Wang, Zhen, Liu, Dexiang, Ho, Roger C.M., Ho, Cyrus S.H.
Publikováno v:
In Behavioural Brain Research 25 June 2024 468
Publikováno v:
In Journal of Colloid And Interface Science 15 June 2024 664:284-298