中文
相关论文

相关论文: Rapid Adaptation of Earth Observation Foundation M…

200 篇论文

With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning…

机器学习 · 计算机科学 2024-08-07 Jihao Gu , Shuai Chen , Zelin Wang , Yibo Zhang , Ping Gong

Low-Rank Adaptation (LoRA) offers a cost-effective solution for fine-tuning large language models (LLMs), but it often produces overconfident predictions in data-scarce few-shot settings. To address this issue, several classical statistical…

Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank Adaptation (LoRA) has been proposed as a solution, yet its…

机器学习 · 计算机科学 2025-06-02 Jabin Koo , Minwoo Jang , Jungseul Ok

Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable parameters has receivedcomparatively little attention. We introduce FoRA, which revisits…

计算与语言 · 计算机科学 2026-05-29 Juneyoung Park , Seongbae Lee , Han-Sang Lee , Kyuho Lee , Minjae Kim , Seungheon Hyeon , Kiduk Kwon , Seongwan Kim , Jaeho Lee

High-quality Earth Observation (EO) imagery is essential for accurate analysis and informed decision making across sectors. However, data scarcity caused by atmospheric conditions, seasonal variations, and limited geographical coverage…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Tiago Sousa , Benoît Ries , Nicolas Guelfi

Foundation models have become prominent in computer vision, achieving notable success in various tasks. However, their effectiveness largely depends on pre-training with extensive datasets. Applying foundation models directly to small…

计算机视觉与模式识别 · 计算机科学 2024-07-02 Bowen Zhang , Ying Chen , Long Bai , Yan Zhao , Yuxiang Sun , Yixuan Yuan , Jianhua Zhang , Hongliang Ren

Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Víctor Barreiro , Johannes Jakubik , Francisco Argüello , Dora B. Heras

Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effective. Inspired by an effort to investigate the different roles…

Federated fine-tuning has emerged as a promising approach to adapt foundation models to downstream tasks using decentralized data. However, real-world deployment remains challenging due to the high computational and communication demands of…

机器学习 · 计算机科学 2025-08-21 Yajie Zhou , Xiaoyi Pang , Zhibo Wang

We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized prompt module to optimize pre-trained model weights and adjust…

机器学习 · 计算机科学 2023-10-17 Arnav Chavan , Zhuang Liu , Deepak Gupta , Eric Xing , Zhiqiang Shen

Low-Rank Adaptation (LoRA) has emerged as one of the most effective, computationally tractable fine-tuning approaches for training Vision-Language Models (VLMs) and Large Language Models (LLMs). LoRA accomplishes this by freezing the…

In this paper, we introduce a subspace-inspired Low-Rank Adaptation (LoRA) method, which is computationally efficient, easy to implement, and readily applicable to large language, multimodal, and diffusion models. Initially, we equivalently…

机器学习 · 计算机科学 2025-03-04 Taiqiang Wu , Jiahao Wang , Zhe Zhao , Ngai Wong

Water segmentation is critical to disaster response and water resource management. Authorities may employ high-resolution photography to monitor rivers, lakes, and reservoirs, allowing for more proactive management in agriculture, industry,…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Hanseon Joo , Eunji Lee , Minjong Cheon

Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Xiangyu Chen , Jing Liu , Ye Wang , Pu Perry Wang , Matthew Brand , Guanghui Wang , Toshiaki Koike-Akino

Federated Learning (FL) facilitates the fine-tuning of Foundation Models (FMs) using distributed data sources, with Low-Rank Adaptation (LoRA) gaining popularity due to its low communication costs and strong performance. While recent work…

机器学习 · 计算机科学 2025-05-27 Zihao Peng , Jiandian Zeng , Boyuan Li , Guo Li , Shengbo Chen , Tian Wang

Low-Rank Adaptation (LoRA) is a widely used finetuning method for large models. Its small memory footprint allows practitioners to adapt large models to specific tasks at a fraction of the cost of full finetuning. Different modifications…

机器学习 · 计算机科学 2025-06-26 Soufiane Hayou , Nikhil Ghosh , Bin Yu

As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight…

机器学习 · 计算机科学 2026-05-15 Yilang Zhang , Xiaodong Yang , Yiwei Cai , Georgios B. Giannakis

Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the…

机器学习 · 计算机科学 2025-12-22 Joanna Sliwa , Frank Schneider , Philipp Hennig , Jose Miguel Hernandez-Lobato

Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuning techniques designed to make the training of language models more efficient. Previous results demonstrated that these methods can even improve performance on some…

Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks while maintaining fine-tuning performance. The low-rank nature of…