Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Si, Chongjie"'
Large language models demonstrate impressive performance on downstream tasks, yet requiring extensive resource consumption when fully fine-tuning all parameters. To mitigate this, Parameter Efficient Fine-Tuning (PEFT) strategies, such as LoRA, have
Externí odkaz:
http://arxiv.org/abs/2409.01035
The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in fine-tuning
Externí odkaz:
http://arxiv.org/abs/2407.05417
Autor:
Si, Chongjie, Wang, Xuehui, Yang, Xue, Xu, Zhengqin, Li, Qingyun, Dai, Jifeng, Qiao, Yu, Yang, Xiaokang, Shen, Wei
Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all parameters becomes unfeasible. To mitigate this, several fine-tuning tech
Externí odkaz:
http://arxiv.org/abs/2405.14739
Weakly Incremental Learning for Semantic Segmentation (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed a
Externí odkaz:
http://arxiv.org/abs/2404.11981
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. The majority of the existing works focuses on constructing robust classifiers to estimate the labeling confidence of can
Externí odkaz:
http://arxiv.org/abs/2312.11034
In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing wo
Externí odkaz:
http://arxiv.org/abs/2305.09897
Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the labe
Externí odkaz:
http://arxiv.org/abs/2207.04197
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.