paper-with-me

홈 › Papers

Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision

2024-06-05 · Minglei Li, Peng Ye, Yongqi Huang, Lin Zhang, Tao Chen, Tong He, Jiayuan Fan, Wanli Ouyang

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 adaptability across diverse tasks. However, striking a balance between high efficiency and robust generalization across tasks remains a challenge for adapter-based methods. We analyze existing methods and find that: 1) parameter sharing is the key to reducing redundancy; 2) more tunable parameters, dynamic allocation, and block-specific design are keys to improving performance. Unfortunately, no previous work considers all these factors. Inspired by this insight, we introduce a novel framework named Adapter-X. First, a Sharing Mixture of Adapters (SMoA) module is proposed to fulfill token-level dynamic allocation, increased tunable parameters, and inter-block sharing at the same time. Second, some block-specific designs like Prompt Generator (PG) are introduced to further enhance the ability of adaptation. Extensive experiments across 2D image and 3D point cloud modalities demonstrate that Adapter-X represents a significant milestone as it is the first to outperform full fine-tuning in both 2D image and 3D point cloud modalities with significantly fewer parameters, i.e., only 0.20% and 1.88% of original trainable parameters for 2D and 3D classification tasks. Our code will be publicly available.

📄 PDF Abstract BibTeX arXiv:2406.03051

Code (0)

등록된 구현이 없습니다.

Tasks

3D Classificationparameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification

2024-03-01 · Mufan Sang, John H. L. Hansen

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-…

Speaker VerificationTransfer Learning

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

2023-04-04 · Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu 외

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific da…

Arithmetic ReasoningLanguage Modelling

AdapterEM: Pre-trained Language Model Adaptation for Generalized Entity Matching using Adapter-tuning

2023-05-30 · John Bosco Mugeni, Steven Lynden, Toshiyuki Amagasa, Akiyoshi Matono

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem…

Binary ClassificationData IntegrationLanguage ModelingLanguage Modelling+1

AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs

2023-04-19 · Shengrui Li, Xueting Han, Jing Bai

Fine-tuning pre-trained models has recently yielded remarkable performance gains in graph neural networks (GNNs). In addition to pre-training techniques, inspired by the latest work in the natural language fields, more r…

Generalization Boundsparameter-efficient fine-tuning

Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

2022-08-15 · Hao Chen, Ran Tao, Han Zhang, Yidong Wang 외

While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on …

Transfer Learning