Zobrazeno 1 - 10
of 391
pro vyhledávání: '"Zeng, Shuang"'
We investigate LoRA in federated learning through the lens of the asymmetry analysis of the learned $A$ and $B$ matrices. In doing so, we uncover that $A$ matrices are responsible for learning general knowledge, while $B$ matrices focus on capturing
Externí odkaz:
http://arxiv.org/abs/2410.01463
High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board se
Externí odkaz:
http://arxiv.org/abs/2409.05352
Federated Learning (FL) is a rising approach towards collaborative and privacy-preserving machine learning where large-scale medical datasets remain localized to each client. However, the issue of data heterogeneity among clients often compels local
Externí odkaz:
http://arxiv.org/abs/2408.12300
The primary goal of continual learning (CL) task in medical image segmentation field is to solve the "catastrophic forgetting" problem, where the model totally forgets previously learned features when it is extended to new categories (class-level) or
Externí odkaz:
http://arxiv.org/abs/2406.13583
Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the text but suffer from the label
Externí odkaz:
http://arxiv.org/abs/2311.08010
Autor:
Zeng, Shuang, Zhu, Lei, Zhang, Xinliang, Chen, Qian, He, Hangzhou, Jin, Lujia, Tian, Zifeng, Ren, Qiushi, Xie, Zhaoheng, Lu, Yanye
Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this dilemma.
Externí odkaz:
http://arxiv.org/abs/2309.11876
End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods adopt an online-trained classification branch to provide pseudo annotation
Externí odkaz:
http://arxiv.org/abs/2308.04949
Incomplete utterance rewriting has recently raised wide attention. However, previous works do not consider the semantic structural information between incomplete utterance and rewritten utterance or model the semantic structure implicitly and insuffi
Externí odkaz:
http://arxiv.org/abs/2307.00866
Distantly-Supervised Named Entity Recognition effectively alleviates the burden of time-consuming and expensive annotation in the supervised setting. But the context-free matching process and the limited coverage of knowledge bases introduce inaccura
Externí odkaz:
http://arxiv.org/abs/2305.04076