Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Liu, Quande"'
Autor:
Liu, Lin, Liu, Quande, Qian, Shengju, Zhou, Yuan, Zhou, Wengang, Li, Houqiang, Xie, Lingxi, Tian, Qi
Video generation is a challenging yet pivotal task in various industries, such as gaming, e-commerce, and advertising. One significant unresolved aspect within T2V is the effective visualization of text within generated videos. Despite the progress a
Externí odkaz:
http://arxiv.org/abs/2406.17777
Generating high-fidelity human video with specified identities has attracted significant attention in the content generation community. However, existing techniques struggle to strike a balance between training efficiency and identity preservation, e
Externí odkaz:
http://arxiv.org/abs/2404.15275
To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships between unsee
Externí odkaz:
http://arxiv.org/abs/2207.08455
Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohi
Externí odkaz:
http://arxiv.org/abs/2206.14467
Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use. In this paper, we study a practical yet challe
Externí odkaz:
http://arxiv.org/abs/2206.13079
Autor:
Yang, Hongzheng, Chen, Cheng, Jiang, Meirui, Liu, Quande, Cao, Jianfeng, Heng, Pheng Ann, Dou, Qi
Test-time adaptation (TTA) has increasingly been an important topic to efficiently tackle the cross-domain distribution shift at test time for medical images from different institutions. Previous TTA methods have a common limitation of using a fixed
Externí odkaz:
http://arxiv.org/abs/2205.13723
Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. However, in many real-world scenarios, the source data may not be accessible during the model adapt
Externí odkaz:
http://arxiv.org/abs/2109.09735
Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. However, despite existing FL algorithms only allow the supervised training setting, most hospitals in realistic
Externí odkaz:
http://arxiv.org/abs/2106.08600
Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection. While at clinical deployment, the models trained in federated learning can still suffer from performance drop when
Externí odkaz:
http://arxiv.org/abs/2103.06030
The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highl
Externí odkaz:
http://arxiv.org/abs/2009.07652