中文
相关论文

相关论文: An Adapter-free Fine-tuning Approach for Tuning 3D…

200 篇论文

Parameter-Efficient Fine-tuning (PEFT) facilitates the fine-tuning of Large Language Models (LLMs) under limited resources. However, the fine-tuning performance with PEFT on complex, knowledge-intensive tasks is limited due to the…

计算与语言 · 计算机科学 2024-06-10 Jitai Hao , WeiWei Sun , Xin Xin , Qi Meng , Zhumin Chen , Pengjie Ren , Zhaochun Ren

Pretrained Foundation Models (PFMs) have transformed numerous applications by enabling efficient adaptation to customized tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient alternative to full fine-tuning,…

机器学习 · 计算机科学 2025-06-16 Baoquan Zhang , Guangning Xu , Michael. K. Ng

The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional…

机器学习 · 计算机科学 2024-04-25 Charith Chandra Sai Balne , Sreyoshi Bhaduri , Tamoghna Roy , Vinija Jain , Aman Chadha

Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these models scale to billions or even trillions of parameters,…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Yi Xin , Jianjiang Yang , Siqi Luo , Yuntao Du , Qi Qin , Kangrui Cen , Yangfan He , Zhiwei Zhang , Bin Fu , Xiaokang Yang , Guangtao Zhai , Ming-Hsuan Yang , Xiaohong Liu

We introduce Monarch Sparse Tuning (MoST), the first reparameterization-based parameter-efficient fine-tuning (PEFT) method tailored for 3D representation learning. Unlike existing adapter-based and prompt-tuning 3D PEFT methods, MoST…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Xu Han , Yuan Tang , Jinfeng Xu , Xianzhi Li

Foundation models pre-trained on large-scale data have been widely witnessed to achieve success in various natural imaging downstream tasks. Parameter-efficient fine-tuning (PEFT) methods aim to adapt foundation models to new domains by…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Wenqiang Zu , Shenghao Xie , Qing Zhao , Guoqi Li , Lei Ma

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…

计算机视觉与模式识别 · 计算机科学 2023-09-01 Haoyu He , Jianfei Cai , Jing Zhang , Dacheng Tao , Bohan Zhuang

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust…

机器学习 · 计算机科学 2024-03-15 Caroline Choi , Yoonho Lee , Annie Chen , Allan Zhou , Aditi Raghunathan , Chelsea Finn

Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Dingkang Liang , Tianrui Feng , Xin Zhou , Yumeng Zhang , Zhikang Zou , Xiang Bai

Transformer-based large pre-trained models have shown remarkable generalization ability, and various parameter-efficient fine-tuning (PEFT) methods have been proposed to customize these models on downstream tasks with minimal computational…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Zichen Miao , Wei Chen , Qiang Qiu

Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to choice for researchers. We find that although PEFT can…

机器学习 · 计算机科学 2025-05-29 Yongkang Liu , Xingle Xu , Ercong Nie , Zijing Wang , Shi Feng , Daling Wang , Qian Li , Hinrich Schütze

Seismic full waveform inversion (FWI) has seen promising advancements through deep learning. Existing approaches typically focus on task-specific models trained and evaluated in isolation that lead to limited generalization across different…

计算工程、金融与科学 · 计算机科学 2024-12-30 Koustav Ghosal , Abhranta Panigrahi , Arnav Chavan , ArunSingh , Deepak Gupta

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

计算与语言 · 计算机科学 2023-05-01 George Pu , Anirudh Jain , Jihan Yin , Russell Kaplan

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Runjia Zeng , Cheng Han , Qifan Wang , Chunshu Wu , Tong Geng , Lifu Huang , Ying Nian Wu , Dongfang Liu

Large models represent a groundbreaking advancement in multiple application fields, enabling remarkable achievements across various tasks. However, their unprecedented scale comes with significant computational costs. These models, often…

机器学习 · 计算机科学 2024-09-17 Zeyu Han , Chao Gao , Jinyang Liu , Jeff Zhang , Sai Qian Zhang

Parameter-efficient fine-tuning (PEFT) has become increasingly important as foundation models continue to grow in both popularity and size. Adapter has been particularly well-received due to their potential for parameter reduction and…

计算机视觉与模式识别 · 计算机科学 2024-06-07 Minglei Li , Peng Ye , Yongqi Huang , Lin Zhang , Tao Chen , Tong He , Jiayuan Fan , Wanli Ouyang

Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter efficient fine-tuning (PEFT) approaches using adapters…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Hayeon Jo , Hyesong Choi , Minhee Cho , Dongbo Min

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

分布式、并行与集群计算 · 计算机科学 2025-10-24 Saransh Gupta , Umesh Deshpande , Travis Janssen , Swami Sundararaman

The emergence of large-scale pre-trained point cloud models has significantly advanced 3D scene understanding, but adapting these models to specific downstream tasks typically demands full fine-tuning, incurring high computational and…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Liyao Tang , Zhe Chen , Dacheng Tao

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Shaochen Zhang , Zekun Qi , Runpei Dong , Xiuxiu Bai , Xing Wei