Zobrazeno 1 - 10
of 5 148
pro vyhledávání: '"Xia, Yong"'
Parameter-efficient fine-tuning (PEFT) techniques have emerged to address issues of overfitting and high computational costs associated with fully fine-tuning in the paradigm of self-supervised learning. Mainstream methods based on PEFT involve addin
Externí odkaz:
http://arxiv.org/abs/2408.15011
Scribble-based weakly supervised segmentation techniques offer comparable performance to fully supervised methods while significantly reducing annotation costs, making them an appealing alternative. Existing methods often rely on auxiliary tasks to e
Externí odkaz:
http://arxiv.org/abs/2408.12814
Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptati
Externí odkaz:
http://arxiv.org/abs/2408.07343
Autor:
Liu, Xiaozhi, Xia, Yong
We propose a novel parametric dictionary learning algorithm for line spectral estimation, applicable in both single measurement vector (SMV) and multiple measurement vectors (MMV) scenarios. This algorithm, termed cubic Newtonized K-SVD (NK-SVD), ext
Externí odkaz:
http://arxiv.org/abs/2408.03708
The challenge of addressing mixed closed-set and open-set label noise in medical image classification remains largely unexplored. Unlike natural image classification where there is a common practice of segregation and separate processing of closed-se
Externí odkaz:
http://arxiv.org/abs/2406.12293
Deep learning-based medical image segmentation models often face performance degradation when deployed across various medical centers, largely due to the discrepancies in data distribution. Test Time Adaptation (TTA) methods, which adapt pre-trained
Externí odkaz:
http://arxiv.org/abs/2405.08270
Autor:
Xie, Yutong, Chen, Qi, Wang, Sinuo, To, Minh-Son, Lee, Iris, Khoo, Ee Win, Hendy, Kerolos, Koh, Daniel, Xia, Yong, Wu, Qi
Current vision-language pre-training (VLP) methodologies predominantly depend on paired image-text datasets, a resource that is challenging to acquire in radiology due to privacy considerations and labelling complexities. Data augmentation provides a
Externí odkaz:
http://arxiv.org/abs/2404.04960
Autor:
Ren, Xinhui, Wang, Jingbo, Yan, Wenming, Xie, Jintao, Wang, Shuangqiang, Wen, Yirong, Xia, Yong
Rotating Radio Transients (RRATs) are a relatively new subclass of pulsars that emit detectable radio bursts sporadically. We conducted an analysis of 10 RRATs observed using the Parkes telescope, with 8 of these observed via the Ultra-Wideband Recei
Externí odkaz:
http://arxiv.org/abs/2402.18035
The majority of classic tensor CP decomposition models are designed for squared loss, employing Euclidean distance as a local proximal term. However, the Euclidean distance is unsuitable for the generalized loss function applicable to various types o
Externí odkaz:
http://arxiv.org/abs/2402.15771
This paper introduces a novel prior called Diversified Block Sparse Prior to characterize the widespread block sparsity phenomenon in real-world data. By allowing diversification on variance and correlation matrix, we effectively address the sensitiv
Externí odkaz:
http://arxiv.org/abs/2402.04646